Fu-Benchmark is a meta-benchmark of the most influential evaluation suites used to measure and rank large language models. Use the search box to filter by name, topic, or model.

All modelsOpen Source modelsOpen Source / TrainingCommercial models All modalitiesTextImage All sizesXS (<2B)S (2–7B)M (7–30B)L (30–70B)XL (70B+) All years20262025202420232022 All countries / regions──────────AggregatesEuropean Union (EU)Europe (EU + UK, CH, NO, IS)EMEA (Europe + Middle East)──────────Individual Countries Benchmarks

#	Name	Topic	Description	Relevance	GitHub ★	Leader	Top %
1	AA-Index o	Multi-domain QA	Comprehensive QA index across diverse domains.	★★★★★		🇺🇸 Grok 4	73.2%
2	AA-LCR O	Long-context reasoning	A challenging benchmark measuring language models' ability to extract, reason about, and synthesize information from long-form documents ranging from 10k to 100k tokens.	★★★★★		🇺🇸 GPT-5 High	76.0%
3	AA-Omniscience O	Knowledge and hallucination	Benchmark measuring factual recall and hallucination across economically relevant domains.	★★★★★		🇺🇸 Gemini 3 Pro Preview	13.0%
4	AceBench O	Industry QA	Industry-focused benchmark assessing domain QA and reasoning.	★★★★★		🇨🇳 Kimi-K2	82.2%
5	ACP-Bench Bool O	Safety evaluation (boolean)	Safety and behavior evaluation with yes/no questions.	★★★★★		🇨🇳 Qwen3-32B	85.1%
6	ACP-Bench MCQ O	Safety evaluation (MCQ)	Safety and behavior evaluation with multiple-choice questions.	★★★★★		🇺🇸 Llama 3.3 70B	82.1%
7	AetherCode o	Code generation	Code generation benchmark for diverse coding tasks.	★★★★★		🇺🇸 Gemini 3 Pro	56.7%
8	AgentCompany o	Agent reasoning	Company-level agent reasoning and decision-making benchmark.	★★★★★		🇺🇸 Claude Sonnet 4.5	41.0%
9	AgentDojo O	Agent evaluation	Interactive evaluation suite for autonomous agents across tools and tasks.	★★★★★		🇺🇸 Claude 3.7 Sonnet	88.7%
10	Agentic Coding O	Agentic coding	Agentic coding benchmark for autonomous software tasks.	★★★★★		🇺🇸 Gemini 3 Flash Preview	53.8%
11	AGIEval (English) O	Exams	English subset of AGIEval; academic and professional exam questions.	★★★★★		🇨🇳 Qwen3-VL 32B Thinking	92.2%
12	AGIEval LSAT-AR o	Law exam reasoning	LSAT Analytical Reasoning subset from AGIEval benchmark.	★★★★★		🇨🇳 Qwen2.5 32B Base	30.4%
13	AI2D O	Diagram understanding (VQA)	Visual question answering over science and diagram images.	★★★★★		🇺🇸 Gemini 3 Pro	98.7%
14	Aider Code Editing o	Code editing	Measures interactive code editing quality within the Aider assistant workflow.	★★★★★		🇺🇸 Gemini 2.5 Pro	89.8%
15	Aider-Polyglot O	Code assistant eval	Aider polyglot coding leaderboard.	★★★★★		🇺🇸 Gemini 3 Pro Preview	92.9%
16	Aider-Polyglot (Diff) O	Code assistant eval	Aider polyglot leaderboard using diff mode (pass@2).	★★★★★		🇺🇸 Gemini 3 Pro Preview	91.9%
17	AIME 2024 O	Math (competition)	American Invitational Mathematics Examination 2024 problems.	★★★★★		🇺🇸 GPT-OSS 120B	96.6%
18	AIME 2024-Ko o	Math (competition, Korean)	Korean translation of AIME 2024 problems.	★★★★★		🇨🇳 Qwen3-30B-A3B-Thinking-2507	80.3%
19	AIME 2025 O	Math (competition)	American Invitational Mathematics Examination 2025 problems.	★★★★★		🇺🇸 Claude Sonnet 4.5	100.0%
20	AInstein-SWE-Bench o	Agentic coding	AInstein agent coding benchmark.	★★★★★		🇺🇸 Gemini 3 Pro	42.8%
21	All-Angles Bench O	Spatial perception	All-Angles benchmark for spatial recognition and 3D perception.	★★★★★		G Step3-VL-10B	57.2%
22	AlpacaEval O	Instruction following	Automatic eval using GPT-4 as a judge.	★★★★★	1849	🇺🇸 Llama-3_1-70B-TFree-HAT-SFT	99.4%
23	AlpacaEval 2.0 O	Instruction following	Updated AlpacaEval with improved prompts and judging.	★★★★★		🇨🇳 DeepSeek R1	87.6%
24	AMC-23 O	Math (competition)	American Mathematics Competition 2023 evaluation.	★★★★★		G QwQ-32B	98.5%
25	AMO-Bench O	Math (competition)	Advanced math olympiad-style benchmark.	★★★★★		🇺🇸 Gemini 3 Pro	72.5%
26	AMO-Bench CH o	Math (competition)	Chinese subset of AMO-Bench.	★★★★★		🇺🇸 Gemini 3 Pro	74.9%
27	AndroidWorld O	Mobile agents	Benchmark for agents operating Android apps via UI automation.	★★★★★		G Seed1.8	70.7%
28	API-Bank o	Tool use	API-Bank tool-use benchmark.	★★★★★		🇺🇸 Llama 3.1 405B	92.0%
29	ARC-AGI-1 O	General reasoning	ARC-AGI Phase 1 aggregate accuracy.	★★★★★		🇺🇸 GPT-5.2 Thinking	86.2%
30	ARC-AGI-2 O	General reasoning	ARC-AGI Phase 2 aggregate accuracy.	★★★★★		🇺🇸 GPT-5.2 Thinking	52.9%
31	ARC Average O	Science QA (average)	Average accuracy across ARC-Easy and ARC-Challenge.	★★★★★		🇺🇸 SmolLM2 1.7B Pretrained	60.5%
32	ARC-Challenge O	Science QA	Hard subset of AI2 Reasoning Challenge; grade-school science.	★★★★★		🇺🇸 Llama 3.1 405B	96.9%
33	ARC-Challenge (DE) o	Science QA (German)	German translation of the ARC Challenge benchmark.	★★★★★		🇺🇸 Llama-3_1-70B-TFree-HAT-SFT	0.7%
34	ARC-Easy O	Science QA	Easier subset of AI2 Reasoning Challenge.	★★★★★		🇺🇸 Gemma 3 PT 27B	89.0%
35	ARC-Easy (DE) o	Science QA (German)	German translation of the ARC Easy science QA benchmark.	★★★★★		🇺🇸 Llama-3_1-70B-TFree-HAT-SFT	0.8%
36	Arena-Hard O	Chat ability	Hard prompts on Chatbot Arena.	★★★★★	920	🇫🇷 Mistral Medium 3	97.1%
37	Arena-Hard V2 O	Chat ability	Updated Arena-Hard v2 prompts on Chatbot Arena.	★★★★★	920	🇨🇳 Qwen3 Max Thinking	90.2%
38	Arena-Hard V2 Creative Writing O	Creative writing	Chatbot Arena Hard V2 creative writing win-rate subset.	★★★★★		🇺🇸 Gemini 3 Pro	93.6%
39	Arena-Hard V2 Hard Prompt O	Chat ability	Chatbot Arena Hard V2 benchmark using the hard prompt win-rate subset.	★★★★★		🇺🇸 Gemini 3 Pro	72.6%
40	ARKitScenes O	3D scene understanding	ARKitScenes benchmark for assessing 3D scene reconstruction and understanding from mixed reality captures.	★★★★★		🇨🇳 Qwen2.5-VL 72B Instruct	61.5%
41	ART Agent Red Teaming O	Agent robustness	Evaluation suite for adversarial red-teaming of autonomous AI agents.	★★★★★		🇺🇸 Claude Opus 4.5	↓ 33.6%
42	ArtifactsBench O	Agentic coding	Artifacts-focused coding and tool-use benchmark evaluating generated code artifacts.	★★★★★		🇺🇸 GPT-5 Thinking	73.0%
43	ASR AMI o	ASR	Automatic speech recognition benchmark on AMI meeting speech.	★★★★★		🇨🇳 Qwen2.5-Omni-3B	↓ 15.1%
44	ASR Earnings22 o	ASR	Automatic speech recognition benchmark on Earnings22 financial calls.	★★★★★		G Whisper-large-V3	↓ 11.3%
45	ASR GigaSpeech o	ASR	Automatic speech recognition benchmark on GigaSpeech.	★★★★★		G Whisper-large-V3	↓ 10.0%
46	ASR LibriSpeech Clean o	ASR	Automatic speech recognition benchmark on LibriSpeech clean split.	★★★★★		🇺🇸 LFM2.5-Audio-1.5B	↓ 1.9%
47	ASR LibriSpeech Other o	ASR	Automatic speech recognition benchmark on LibriSpeech other split.	★★★★★		G Whisper-large-V3	↓ 3.9%
48	ASR SPGISpeech o	ASR	Automatic speech recognition benchmark on SPGISpeech.	★★★★★		🇺🇸 LFM2.5-Audio-1.5B	↓ 2.8%
49	ASR TED-LIUM o	ASR	Automatic speech recognition benchmark on TED-LIUM.	★★★★★		🇺🇸 LFM2.5-Audio-1.5B	↓ 3.5%
50	ASR VoxPopuli o	ASR	Automatic speech recognition benchmark on VoxPopuli.	★★★★★		🇨🇳 Qwen2.5-Omni-3B	↓ 5.6%
51	AstaBench O	Agent evaluation	Evaluates science agents across literature understanding, data analysis, planning, tool use, coding, and search.	★★★★★		🇺🇸 Claude Sonnet 4	53.0%
52	AttaQ O	Safety / jailbreak	Adversarial jailbreak suite measuring refusal robustness against targeted attack prompts.	★★★★★		G Granite 3.3 8B Instruct	88.5%
53	AutoCodeBench O	Autonomous coding	End-to-end autonomous coding benchmark with unit-test based execution across diverse repositories and tasks.	★★★★★		🇺🇸 Claude Opus 4 (Thinking)	52.4%
54	AutoCodeBench-Lite O	Autonomous coding	Lite version of AutoCodeBench focusing on smaller tasks with the same end-to-end, unit-test-based evaluation.	★★★★★		🇺🇸 Claude Opus 4	64.5%
55	AutoLogi o	Logical reasoning	AutoLogi benchmark evaluating automated logical reasoning accuracy.	★★★★★		🇺🇸 Claude Sonnet 4	89.8%
56	BALROG O	Agent robustness	Benchmark for assessing LLM agents under adversarial and out-of-distribution tool-use scenarios.	★★★★★		🇺🇸 Grok 4	43.6%
57	BBH O	Multi-task reasoning	Hard subset of BIG-bench with diverse reasoning tasks.	★★★★★	510	🇨🇳 ERNIE 4.5 424B A47B	94.3%
58	BBQ O	Bias evaluation	Bias Benchmark for Question Answering evaluating social biases across contexts.	★★★★★		🇫🇷 Mixtral 8x 7B	56.0%
59	BeaverTails o	Safety / harmfulness	Safety benchmark evaluating harmfulness in model responses.	★★★★★		G IQuest-Coder-V1-40B-Thinking	76.7%
60	BeyondAIME o	Math (beyond AIME)	Advanced math problems exceeding AIME difficulty.	★★★★★		🇺🇸 Gemini 3 Pro	83.0%
61	BFCL O	Code reasoning	Benchmark for functional code correctness and logic.	★★★★★		🇨🇳 Qwen3-4B	95.0%
62	BFCL Live v2 O	Finance QA	Financial compliance and literacy questions from the BFCL Live v2 benchmark.	★★★★★		🇺🇸 o1 Mini	81.0%
63	BFCL v2 o	Code reasoning	Second release of the BFCL benchmark focusing on functional code correctness and logic.	★★★★★		G MobileLLM P1	29.4%
64	BFCL v3 O	Code reasoning	Benchmark for functional code correctness and logic (v3).	★★★★★		🇨🇳 GLM 4.5	77.8%
65	BFCL v3 (Live) o	Tool calling	BFCL v3 Live subset for real-time tool calling evaluation.	★★★★★		🇨🇳 Qwen3-30B-A3B-Thinking-2507	82.9%
66	BFCL v3 (Multi-Turn) o	Tool calling	BFCL v3 Multi-Turn subset for multi-turn tool calling evaluation.	★★★★★		🇨🇳 Qwen3-30B-A3B-Thinking-2507	53.6%
67	BFCL v4 O	Code reasoning	BFCL v4 benchmark for functional code correctness and logic.	★★★★★		🇺🇸 Claude Opus 4.5	77.5%
68	BIG-Bench o	Multi-task reasoning	BIG-bench overall performance (original).	★★★★★	3110	🇺🇸 Gemma 2 7B	55.1%
69	BIG-Bench Extra Hard o	Multi-task reasoning	Extra hard subset of BIG-bench tasks.	★★★★★		G Ling 1T	47.3%
70	BigCodeBench O	Code Generation	BigCodeBench evaluates large language models on practical code generation tasks with unit-test verification.	★★★★★		G MiMo V2 Flash Base	70.1%
71	BigCodeBench Hard O	Code generation (hard)	Harder variant of BigCodeBench testing complex programming and library tasks with function-level code generation.	★★★★★		🇺🇸 Claude 3.7 Sonnet (2025-02-19)	35.8%
72	BIOBench o	Biology reasoning	Biology knowledge and reasoning benchmark.	★★★★★		🇺🇸 Gemini 3 Pro	51.9%
73	BioLP-Bench o	Biomedical NLP	Comprehensive biomedical language processing benchmark evaluating LLMs across tasks like NER, relation extraction, and QA.	★★★★★		🇺🇸 Grok 4	47.0%
74	Bird-SQL O	Text-to-SQL	Natural language to SQL generation benchmark.	★★★★★		🇺🇸 Gemini 2.0 Pro	59.3%
75	BLINK O	Multimodal grounding	Evaluates visual-language grounding and reference resolution to reduce hallucinations.	★★★★★		🇺🇸 Gemini 3 Pro	87.4%
76	BoB-HVR O	Composite capability index	Hard, Versatile, and Relevant composite score across eight capability buckets.	★★★★★		🇺🇸 Llama 3 70B	9.0%
77	BOLD o	Bias evaluation	Bias in Open-ended Language Dataset probing demographic biases in text generation.	★★★★★		🇫🇷 Mixtral 8x 7B	↓ 0.1%
78	BoolQ O	Reading comprehension	Yes/no QA from naturally occurring questions.	★★★★★	171	G Marin-32B-Mantis	89.4%
79	Borda Count (Multilingual) o	Aggregate ranking	Borda count aggregate ranking across multilingual benchmarks; lower is better.	★★★★★		🇨🇳 Qwen3-32B	↓ 2.9%
80	BrowseComp O	Web browsing	Web browsing comprehension and competence benchmark.	★★★★★		G MiroThinker-v1.5-235B	69.8%
81	BrowseComp (With Content Manager) O	Web browsing	BrowseComp benchmark evaluated with content manager assistance.	★★★★★		🇨🇳 LongCat-Flash-Thinking-2601	73.1%
82	BrowseComp_zh O	Web browsing (Chinese)	Chinese variant of the BrowseComp web browsing benchmark.	★★★★★		G Seed1.8	81.3%
83	BRuMo25 o	Math competition	BruMo 2025 olympiad-style mathematics benchmark.	★★★★★		🇺🇸 QuestA Nemotron 1.5B	69.5%
84	BuzzBench O	Humor analysis	A humour analysis benchmark.	★★★★★		🇺🇸 Gemini 2.5 Pro	71.1%
85	C-Eval O	Chinese exams	Chinese college-level exam benchmark.	★★★★★	1768	🇨🇳 Qwen3 Max Thinking	93.7%
86	C3-Bench o	Reasoning (Chinese)	Comprehensive Chinese reasoning capability benchmark.	★★★★★	35	🇨🇳 GLM-4.5 Base	83.1%
87	CaseLaw v2 O	Legal reasoning	U.S. case law benchmark evaluating legal reasoning and judgment over court opinions.	★★★★★		🇺🇸 GPT-4.1	78.1%
88	CC-OCR O	OCR (cross-lingual)	Cross-lingual OCR benchmark evaluating character recognition across mixed-language documents.	★★★★★		🇨🇳 Qwen3-VL-235B-A22B Thinking	81.5%
89	CFEval o	Coding ELO / contest eval	Contest-style coding evaluation with ELO-like scoring.	★★★★★		🇨🇳 Qwen3-235B-A22B-Thinking-2507	2134
90	CGBench o	Long video QA	Cartoon/CG long video question answering benchmark.	★★★★★		🇺🇸 Gemini 2.5 Pro	64.6%
91	Charades-STA O	Video grounding	Charades-STA temporal grounding (mIoU).	★★★★★		🇨🇳 Seed1.5-VL-Thinking	64.0%
92	ChartMuseum o	Chart understanding	Large-scale curated collection of charts for evaluating parsing, grounding, and reasoning.	★★★★★		🇺🇸 GPT-5 mini	63.3%
93	ChartQA O	Chart understanding (VQA)	Visual question answering over charts and plots.	★★★★★		🇨🇳 Keye-VL-1.5-8B	94.1%
94	ChartQA-Pro o	Chart understanding (VQA)	Professional-grade chart question answering with diverse chart types and complex reasoning.	★★★★★		🇨🇳 GLM-4.6V	65.5%
95	CharXiv (DQ) O	Chart description (PDF)	Scientific chart/table descriptive questions from arXiv PDFs.	★★★★★		🇺🇸 o3-high	95.0%
96	CharXiv (RQ) O	Chart reasoning (PDF)	Scientific chart/table reasoning questions from arXiv PDFs.	★★★★★		🇺🇸 GPT-5.2 Thinking	82.1%
97	Chinese SimpleQA o	QA (Chinese)	Chinese variant of the SimpleQA benchmark.	★★★★★		🇨🇳 Kimi-K2 Base	77.6%
98	CLIcK o	Korean instruction following	Korean long-form instruction-following benchmark.	★★★★★		🇨🇳 DeepSeek V3.2-Thinking	86.3%
99	CloningScenarios o	Biosecurity refusal	Safety benchmark that red-teams models with cloning-related misuse scenarios to measure compliance and refusal rates.	★★★★★		🇺🇸 Grok 4	↓ 45.0%
100	CLUEWSC o	Coreference reasoning (Chinese)	Chinese Winograd Schema-style coreference benchmark from CLUE.	★★★★★		🇨🇳 DeepSeek R1	92.8%
101	CMath o	Math (Chinese)	Chinese mathematics benchmark.	★★★★★		🇨🇳 ERNIE 4.5 424B A47B	96.7%
102	CMMLU O	Chinese multi-domain	Chinese counterpart to MMLU.	★★★★★	781	🇨🇳 Qwen2.5 Max	91.9%
103	CNMO 2024 o	Math (competition)	China National Mathematical Olympiad 2024 evaluation set.	★★★★★		G openPangu-R-72B-2512 Slow Thinking	82.8%
104	Codeforces O	Competitive programming	Competitive programming performance on Codeforces problems (ELO).	★★★★★		🇺🇸 o4 mini	2719
105	COLLIE o	Instruction following	Comprehensive instruction-following evaluation suite.	★★★★★	55	🇺🇸 GPT-5	99.0%
106	Collie-Hard o	Instruction following	Hard subset of Collie instruction-following tasks.	★★★★★		🇺🇸 GPT-5 High	99.0%
107	CommonsenseQA O	Commonsense QA	Multiple-choice QA requiring commonsense knowledge.	★★★★★		🇨🇳 Qwen2.5 32B Base	88.5%
108	Complex Workflow o	Complex workflows	Complex workflow benchmark for economically valuable tasks.	★★★★★		🇺🇸 Gemini 3 Pro	58.2%
109	COPA o	Causal reasoning	Choice of Plausible Alternatives.	★★★★★		G Marin-32B-Bison	94.0%
110	CorpusQA O	Long-context QA	Question answering over large text corpora.	★★★★★		🇺🇸 GPT-5	81.6%
111	CountBench O	Visual counting	Object counting and numeracy benchmark for visual-language models across varied scenes.	★★★★★		🇺🇸 Gemini 3 Pro	97.3%
112	CountBenchQA O	Visual counting QA	Visual question answering benchmark focused on counting objects across varied scenes.	★★★★★		G Moondream-9B-A2B	93.2%
113	Countdown o	Planning and reasoning	Countdown-style reasoning and planning benchmark.	★★★★★		G K2-V2	75.6%
114	Countix o	Video counting	Video-based counting benchmark for multiple objects.	★★★★★		G Seed1.8	31.0%
115	CRAG o	Retrieval QA	Complex Retrieval-Augmented Generation benchmark for grounded question answering.	★★★★★		G Jamba Mini 1.6	76.2%
116	Creative Story‑Writing Benchmark V3 O	Creative writing	Story writing benchmark evaluating creativity, coherence, and style (v3).	★★★★★	291	🇨🇳 Kimi-K2-Instruct-0905	8.7%
117	Longform Creative Writing O	Creative writing	Longform creative writing evaluation (EQ-Bench).	★★★★★	20	🇺🇸 Claude Sonnet 4.5 (Thinking)	79.8%
118	Creative Writing v3 O	Creative writing	A LLM-judged creative writing benchmark.	★★★★★	54	🇺🇸 o3	1661
119	Complex Research using Integrated Thinking – Physics Test O	Reasoning	CritPt (Complex Research using Integrated Thinking – Physics Test) benchmark.	★★★★★		🇺🇸 GPT-5 (High, Code & Web)	12.6%
120	CRUX-I O	Code reasoning	Code Reasoning and Understanding eXam – Interactive.	★★★★★		🇺🇸 Gemini 3 Pro Preview	98.8%
121	CRUX-O O	Code reasoning	Code Reasoning and Understanding eXam – Offline.	★★★★★		G IQuest-Coder-V1-40B-Loop-Thinking	99.4%
122	CruxEval O	Code reasoning	Mathematical coding challenge set from the CruxEval benchmark.	★★★★★		🇨🇳 Qwen3-30B-A3B-Instruct-2507	86.8%
123	CSimpleQA o	QA	Chinese SimpleQA benchmark variant (short factual questions).	★★★★★		🇨🇳 Kimi-K2 Base	77.6%
124	Customer Support Q&A o	Customer support QA	Customer support question answering benchmark.	★★★★★		G Seed1.8	69.0%
125	CUTE o	English characters	CUTE aggregate capability score.	★★★★★		🇺🇸 Bolmo 7B	78.6%
126	CV-Bench O	Computer vision QA	Diverse CV tasks for VLMs.	★★★★★		🇺🇸 Gemini 3 Pro	92.0%
127	CVTG-2K CLIPScore o	Text rendering	CVTG-2K CLIPScore for text rendering in image generation.	★★★★★		G Seedream 4.5	0.8%
128	CVTG-2K NED o	Text rendering	CVTG-2K normalized edit distance (NED) for text rendering.	★★★★★		🇨🇳 GLM-Image	1.0%
129	CVTG-2K Word Accuracy o	Text rendering	CVTG-2K word accuracy for text rendering in images.	★★★★★		🇨🇳 GLM-Image	0.9%
130	CyBench o	Cybersecurity CTF	Framework with 40 professional-level CTF tasks evaluating LLMs' practical cybersecurity capabilities.	★★★★★		🇺🇸 o3 mini	↓ 22.5%
131	CyberGym o	Cybersecurity tasks	Benchmark for cybersecurity-related coding and reasoning tasks.	★★★★★		🇺🇸 Claude Opus 4.5 Thinking	50.6%
132	DA-2K o	Spatial reasoning	2D/3D spatial reasoning benchmark.	★★★★★		🇨🇳 Seed1.5-VL-Thinking	85.3%
133	Deep Planning o	Planning and reasoning	Benchmark evaluating deep planning and multi-step reasoning capabilities.	★★★★★		🇺🇸 GPT-5.2 Thinking	44.6%
134	DeepConsult o	Agentic writing	Agentic consulting and writing benchmark.	★★★★★		🇺🇸 GPT-5 High	57.2%
135	DeepMind Mathematics o	Math reasoning	Synthetic math problem sets from DeepMind covering arithmetic, algebra, calculus, and more.	★★★★★		G Granite-4.0-H-Small	59.3%
136	DeepResearchBench o	Agentic research writing	Research-oriented agentic writing and planning benchmark.	★★★★★		🇺🇸 Gemini 3 Pro	49.6%
137	DeepSearchQA o	Deep web search QA	Multi-step web search and question answering benchmark.	★★★★★		🇨🇳 Kimi-K2.5 Thinking	77.1%
138	Design2Code O	Coding (UI)	Translating UI designs into code.	★★★★★		🇨🇳 Qwen3-VL-235B-A22B Thinking	93.4%
139	DesignArena O	Generative design	Leaderboard tracking generative design systems across layout, branding, and marketing tasks.	★★★★★		🇺🇸 Claude Sonnet 4.5 (Thinking)	1410
140	DetailBench o	Spot small mistakes	Evaluates whether LLMs can notice subtle errors and minor inconsistencies in text.	★★★★★		🇺🇸 Llama 4 Maverick	8.7%
141	DiscoX o	Agentic writing	DiscoX benchmark for agentic writing and reasoning.	★★★★★		🇺🇸 Gemini 3 Pro	75.8%
142	Do-Anything-Now o	Safety / jailbreak	Resistance to Do Anything Now (DAN) style jailbreak prompts.	★★★★★		G IQuest-Coder-V1-40B-Thinking	97.7%
143	Do-Not-Answer o	Safety / refusal	Evaluates a model's ability to refuse unsafe or disallowed requests.	★★★★★		G K2-THINK	88.0%
144	DocMath O	Document math	Math reasoning on document-based problems.	★★★★★		🇺🇸 GPT-5	67.6%
145	DocVQA O	Document understanding (VQA)	Visual question answering over scanned documents.	★★★★★		🇨🇳 Seed1.5-VL-Thinking	96.9%
146	Dolphin-Page o	Document OCR	Dolphin Page benchmark measuring OCR fidelity and structured extraction on multi-layout documents.	★★★★★		🇺🇸 Dolphin 1.5	↓ 7.4%
147	DPG-Bench O	Text rendering	DPG-Bench score for text rendering in image generation.	★★★★★		G Seedream 4.5	88.6%
148	DROP O	Reading + reasoning	Discrete reasoning over paragraphs (addition, counting, comparisons).	★★★★★		🇨🇳 Kimi K2 Instruct	93.5%
149	DUDE o	Multimodal long-context	Long-context multimodal understanding benchmark.	★★★★★		🇺🇸 Gemini 3 Pro	70.1%
150	DynaMath O	Math reasoning (video)	Dynamic/video-based mathematical reasoning evaluating temporal and visual understanding.	★★★★★		🇺🇸 GPT-4o	63.7%
151	Economically important tasks o	Industry QA (cross-domain)	Evaluation suite of real-world, economically impactful tasks across key industries and workflows.	★★★★★		🇺🇸 GPT-5	47.1%
152	Education o	Economics/education	Education field evaluation (economically valuable tasks).	★★★★★		G Seed1.8	60.8%
153	EgoSchema O	Egocentric video QA	EgoSchema validation accuracy.	★★★★★		🇨🇳 Qwen2-VL 72B Instruct	77.9%
154	EgoTempo o	Egocentric temporal reasoning	Egocentric video temporal reasoning benchmark.	★★★★★		G Seed1.8	67.0%
155	EIFBench o	Instruction following	Complex instruction-following benchmark.	★★★★★		🇺🇸 GPT-5 High	66.7%
156	EmbSpatialBench O	Spatial understanding	Embodied spatial understanding benchmark evaluating navigation and localization.	★★★★★		🇨🇳 Qwen3-VL-235B-A22B Thinking	84.3%
157	EMMA o	Multimodal reasoning	EMMA benchmark for multimodal reasoning.	★★★★★		🇺🇸 Gemini 3 Pro	66.5%
158	Enamel o	Composite capability	Composite capability benchmark capturing broad model performance (Enamel score).	★★★★★		G Rnj-1	49.0%
159	EnConda-Bench o	Code editing	English code editing benchmark for applying conditional modifications.	★★★★★		G Youtu-LLM-2B	21.5%
160	EnigmaEval O	Challenging puzzles	Challenging puzzle benchmark.	★★★★★		🇺🇸 Gemini 3 Pro	17.8%
161	Enterprise RAG o	Retrieval-augmented generation	Enterprise retrieval-augmented generation evaluation covering internal knowledge bases.	★★★★★		🇺🇸 Apriel Nemotron 15B Thinker	69.2%
162	EQ-Bench O	Reasoning	General reasoning benchmark assessing equation/logic capabilities.	★★★★★	352	G Jan v1 2509	85.0%
163	EQ-Bench 3 O	Emotional intelligence (roleplay)	A benchmark measuring emotional intelligence in challenging roleplays, judged by Sonnet 3.7.	★★★★★	21	🇨🇳 Kimi K2 Instruct	1555
164	ERQA O	Spatial reasoning	Spatial recognition and reasoning QA benchmark (ERQA).	★★★★★		🇺🇸 Gemini 3 Flash	71.0%
165	EvalPerf O	Code evaluation performance	Measures performance of LLM code evaluation, including runtime, memory, and efficiency metrics.	★★★★★		🇺🇸 GPT-4o (2024-08-06)	100.0%
166	EvalPlus O	Code generation	Aggregated code evaluation suite from EvalPlus.	★★★★★	1577	🇺🇸 o1 Mini	89.0%
167	EVG o	Document OCR	EVG document OCR benchmark evaluating recognition accuracy and layout extraction.	★★★★★		🇺🇸 Dolphin 1.5	↓ 3.0%
168	EXECUTE o	Multilingual character tasks	Multilingual character-level evaluation benchmark.	★★★★★		🇺🇸 Bolmo 7B	71.6%
169	FACTS Benchmark Suite o	Held out internal grounding, parametric, MM, and search retrieval benchmarks	Comprehensive factuality benchmark suite covering held-out internal grounding, parametric knowledge, multimodal understanding, and search retrieval benchmarks.	★★★★★		🇺🇸 Gemini 3 Pro	70.5%
170	FACTS Grounding O	Grounding / factuality	Grounded factuality benchmark evaluating model alignment with source facts.	★★★★★		🇨🇳 Kimi K2 Instruct	88.5%
171	FActScore o	Hallucination rate on open-source prompts	Measures hallucination rate on an open-source prompt suite; lower is better.	★★★★★		🇺🇸 GPT-5	↓ 1.0%
172	FaithJudge (1-Hallu.) o	Hallucination detection	FaithJudge hallucination rate with 1-hallucination metric (lower is better).	★★★★★		G Moonlight-Instruct	↓ 56.0%
173	Meta Score Agent O	Composite capability index		★★★★★		🇺🇸 Claude Opus 4.5	100.0%
174	Meta Score Code O	Composite capability index		★★★★★		🇺🇸 Claude Opus 4.5	100.0%
175	Meta Score Math O	Composite capability index		★★★★★		🇨🇳 Qwen3-VL-235B-A22B Instruct	100.0%
176	Meta Score OCR O	Composite capability index		★★★★★		🇺🇸 o3 (Low)	80.0%
177	Meta Score Safety O	Composite safety index		★★★★★		G Granite 3.3 8B Instruct	70.0%
178	Meta Score STEM O	Composite capability index		★★★★★		🇨🇳 Qwen3-VL-235B-A22B Instruct	100.0%
179	Meta Score Text O	Composite capability index		★★★★★		🇺🇸 Claude Opus 4.5	85.7%
180	Meta Score Visual O	Composite capability index		★★★★★		🇺🇸 Gemini 3 Pro	100.0%
181	Meta Score Writing O	Composite capability index		★★★★★		🇨🇳 Qwen3 235B A22B Instruct 2507	60.0%
182	FigQA o	Figure understanding and QA	Figure question answering benchmark evaluating visual reasoning over scientific figures and diagrams.	★★★★★		🇺🇸 Grok 4.1 (Thinking)	34.0%
183	FinanceReasoning o	Financial reasoning	Financial reasoning benchmark evaluating quantitative and qualitative finance problem solving.	★★★★★		G Ling 1T	87.5%
184	FinanceAgent o	Agentic finance tasks	Interactive financial agent benchmark requiring multi-step tool use.	★★★★★		🇺🇸 Claude Sonnet 4.5	55.3%
185	FinanceBench (FullDoc) o	Finance QA	FinanceBench full-document question answering benchmark requiring long-context financial understanding.	★★★★★		G Jamba Mini 1.6	45.4%
186	FinSearchComp O	Financial retrieval	Financial search and comprehension benchmark measuring retrieval grounded reasoning over financial content.	★★★★★		🇺🇸 Grok 4	68.9%
187	FinSearchComp-CN O	Financial retrieval (Chinese)	Chinese financial search and comprehension benchmark measuring retrieval-grounded reasoning over regional financial content.	★★★★★		G doubao-1-5-vision-pro	54.2%
188	FinSearchComp (T2&T3) o	Finance search	Finance search competition tasks (tracks T2 and T3).	★★★★★		🇺🇸 GPT-5 High	64.5%
189	Flame-React-Eval o	Frontend coding	Front-end React coding tasks and evaluation.	★★★★★		🇨🇳 GLM-4.6V	86.3%
190	Flores o	Machine translation (multilingual)	FLORES multilingual translation benchmark.	★★★★★		G EuroLLM-22B	88.9%
191	Fox-Page-cn o	Document OCR (Chinese)	Fox Page benchmark evaluating OCR accuracy and layout understanding on Chinese document pages.	★★★★★		🇺🇸 Dolphin 1.5	↓ 0.8%
192	Fox-Page-en o	Document OCR (English)	Fox Page benchmark evaluating OCR accuracy and layout understanding on English document pages.	★★★★★		🇺🇸 Dolphin 1.5	↓ 0.7%
193	FRAMES O	Interactive reasoning	Frame-based interactive reasoning and dialogue benchmark.	★★★★★		🇨🇳 Tongyi DeepResearch	90.6%
194	FreshQA o	Recency QA	Question answering benchmark emphasizing up-to-date knowledge and recency.	★★★★★		🇨🇳 Qwen3-4B Thinking 2507	66.9%
195	FrontierScience o	Science reasoning	Frontier-level scientific reasoning and QA benchmark.	★★★★★		🇺🇸 GPT-5.2	25.2%
196	FSC-147 o	Few-shot counting	Few-shot counting benchmark across 147 categories.	★★★★★		G Seed1.8	33.8%
197	FullStackBench O	Full-stack development	End-to-end web/app development tasks and evaluation.	★★★★★		🇺🇸 Claude Opus 4.5	72.3%
198	GAIA O	General AI tasks	Comprehensive benchmark for agentic tasks.	★★★★★		G Seed1.8	87.4%
199	GAIA 2 O	General agent tasks	Grounded agentic intelligence benchmark version 2 covering multi-tool tasks.	★★★★★		🇺🇸 GPT-5 High	42.1%
200	GAOKAO-Bench o	Chinese exams	GAOKAO benchmark measuring Chinese college entrance exam performance.	★★★★★		🇨🇳 Qwen3-30B-A3B-Instruct-2507	94.5%
201	GDPVal O	General capability	GDPVal benchmark evaluating broad general capabilities of LLMs across diverse tasks.	★★★★★		🇺🇸 GPT-5.2 Thinking	70.9%
202	General Tool Use O	Tool use	General tool-use benchmark covering web and API tasks.	★★★★★		🇺🇸 Claude Opus 4.5	78.9%
203	GeoBench1 o	Geospatial reasoning	Geospatial visual QA and reasoning (set 1).	★★★★★		🇨🇳 GLM-4.5V	79.7%
204	Global-MMLU O	Multi-domain knowledge (global)	Full Global-MMLU evaluation across diverse languages and regions.	★★★★★		🇨🇳 DeepSeek V3.2-Exp	82.0%
205	Global-MMLU-Lite O	Multi-domain knowledge (global)	Lightweight global variant of MMLU covering diverse languages and regions.	★★★★★		🇺🇸 Gemini 2.5 Pro	89.2%
206	Global PIQA o	Commonsense reasoning across 100 Languages and Cultures	Physical commonsense reasoning benchmark spanning 100 languages and diverse cultural contexts.	★★★★★		🇺🇸 Gemini 3 Pro	93.4%
207	Gorilla Benchmark API Bench o	Tool use	Gorilla API Bench tool-use evaluation.	★★★★★		🇺🇸 Llama 3.1 405B	35.3%
208	GPQA O	Graduate-level QA	Graduate-level question answering evaluating advanced reasoning.	★★★★★	406	🇺🇸 GPT-5.2 Thinking	92.4%
209	GPQA-diamond O	Graduate-level QA	Hard subset of GPQA (diamond level).	★★★★★		🇺🇸 GPT-5.2 Thinking XHigh	92.9%
210	GRE Math maj@16 o	Math (standardized tests)	GRE quantitative section evaluated via majority voting over 16 samples.	★★★★★		🇨🇳 Qwen2 7B	58.5%
211	Ground-UI-1K O	GUI grounding	Accuracy on the Ground-UI-1K grounding benchmark.	★★★★★		🇨🇳 Qwen2.5-VL 72B	85.4%
212	GSM-Infinite Hard (128K) o	Math reasoning	GSM-Infinite Hard benchmark at 128K context.	★★★★★		G MiMo V2 Flash Base	29.0%
213	GSM-Infinite Hard (16K) o	Math reasoning	GSM-Infinite Hard benchmark at 16K context.	★★★★★		🇨🇳 DeepSeek V3.2-Exp	50.4%
214	GSM-Infinite Hard (32K) o	Math reasoning	GSM-Infinite Hard benchmark at 32K context.	★★★★★		🇨🇳 DeepSeek V3.2-Exp	45.2%
215	GSM-Infinite Hard (64K) o	Math reasoning	GSM-Infinite Hard benchmark at 64K context.	★★★★★		🇨🇳 DeepSeek V3.1	34.7%
216	GSM-Plus O	Math (grade-school, enhanced)	Enhanced GSM-style grade-school math benchmark variant.	★★★★★		🇨🇳 Qwen3-4B	82.1%
217	GSM-Symbolic o	Math reasoning	Symbolic reasoning variant of GSM that tests algebraic manipulation and arithmetic with structured problems.	★★★★★		G Granite-4.0-H-Small	87.4%
218	GSM8K O	Math (grade-school)	Grade-school math word problems requiring multi-step reasoning.	★★★★★	1322	🇨🇳 Kimi K2 Instruct	97.3%
219	GSM8K (DE) o	Math (grade-school, German)	German translation of the GSM8K grade-school math word problems.	★★★★★		🇺🇸 Llama-3_1-70B-TFree-HAT-SFT	0.6%
220	GSM8K-Ko o	Math (grade-school, Korean)	Korean translation of the GSM8K grade-school math word problems.	★★★★★		🇨🇳 Qwen3-30B-A3B	88.1%
221	GSM8K Platinum o	Math (grade-school, hard)	Harder subset/setting of GSM8K grade-school math problems.	★★★★★		🇨🇳 Kimi-Linear-Base	89.6%
222	GSO Benchmark O	Code generation	LiveCodeBench GSO benchmark.	★★★★★		🇺🇸 o3-high	8.8%
223	HAE-RAE Bench o	Korean language understanding	Korean language understanding benchmark evaluating knowledge and reasoning.	★★★★★		G Kanana-1.5-32.5B-Base	90.7%
224	HallusionBench O	Multimodal hallucination	Benchmark for evaluating hallucination tendencies in multimodal LLMs.	★★★★★		🇺🇸 Gemini 3 Pro	69.9%
225	HarmBench o	Safety	Harmfulness and safety compliance benchmark across a variety of risky prompts.	★★★★★		G IQuest-Coder-V1-40B-Thinking	94.8%
226	HarmfulQA o	Safety	Harmful question set testing models' ability to avoid unsafe answers.	★★★★★	104	G K2-THINK	99.0%
227	HealthBench O	Medical QA	Comprehensive medical knowledge and clinical reasoning benchmark across specialties and tasks.	★★★★★		🇺🇸 GPT-5	67.2%
228	HealthBench-Hard o	Medical QA (hard)	Challenging subset of HealthBench focusing on complex, ambiguous clinical cases.	★★★★★		🇺🇸 GPT-5	46.2%
229	HealthBench-Hard Hallucinations o	Medical hallucination safety	Measures hallucination and unsafe medical advice under hard clinical scenarios.	★★★★★		🇺🇸 GPT-5	↓ 1.6%
230	HellaSwag O	Commonsense reasoning	Adversarial commonsense sentence completion.	★★★★★	220	🇨🇳 DeepSeek V3 Base	96.4%
231	HellaSwag (DE) o	Commonsense reasoning (German)	German translation of the HellaSwag commonsense benchmark.	★★★★★		🇺🇸 Llama-3_1-70B-TFree-HAT-SFT	0.7%
232	HELMET LongQA o	Long-context QA	Long-context subset of the HELMET benchmark focusing on grounded question answering.	★★★★★		G Jamba Mini 1.6	46.9%
233	HeroBench O	Long-horizon planning	Benchmark for Long-Horizon Planning and Structured Reasoning in Virtual Worlds.	★★★★★		🇺🇸 Grok 4	91.7%
234	HHEM v2.1 O	Hallucination detection	Hughes Hallucination Evaluation Model (Vectara) — lower is better.	★★★★★		G AntGroup Finix_S1_32b	↓ 0.6%
235	HiddenMath O	Math reasoning	Mathematical reasoning benchmark referenced in recent model cards.	★★★★★		🇺🇸 Gemini 2.0 Pro	65.2%
236	HLE O	Multi-domain reasoning	Challenging LLMs at the frontier of human knowledge.	★★★★★	1085	🇺🇸 Gemini 3 Pro	45.8%
237	HLE Overconfidence O	Overconfidence / safety	Overconfidence rate derived from Humanity's Last Exam evaluations.	★★★★★		🇺🇸 GPT-5.2	↓ 43.7%
238	HLE (Text Only) O	Advanced reasoning	Humanity's Last Exam benchmark restricted to text-only inputs.	★★★★★	1085	🇺🇸 Gemini 3 Pro	45.8%
239	HLE-VL o	Holistic language evaluation (vision-language)	Vision-language HLE benchmark.	★★★★★		🇺🇸 Gemini 3 Pro	36.0%
240	HLE (With Tools) O	Tool-augmented reasoning	Humanity's Last Exam benchmark evaluated with tool access.	★★★★★	1085	🇨🇳 Kimi-K2.5 Thinking	50.2%
241	HMMT o	Math (competition)	Harvard–MIT Mathematics Tournament problems.	★★★★★		🇺🇸 GPT-5 pro	100.0%
242	HMMT 2025 O	Math (competition)	Harvard–MIT Mathematics Tournament 2025 problems.	★★★★★		🇺🇸 Gemini 3 Pro	99.8%
243	HMMT Feb 2025 O	Math (competition)	Harvard–MIT Mathematics Tournament February 2025 problems.	★★★★★		🇺🇸 GPT-5.2 Thinking	99.4%
244	HMMT Nov 2025 O	Math (competition)	Harvard–MIT Mathematics Tournament November 2025 problems.	★★★★★		🇨🇳 Qwen3 Max Thinking	94.7%
245	HotpotQA o	Multi-hop QA	Explainable multi-hop QA with supporting facts.	★★★★★		🇨🇳 Qwen 3 0.6B	64.0%
246	HRBench 4K O	Hallucination robustness	Hallucination robustness benchmark with 4K token contexts.	★★★★★		🇨🇳 Qwen3-VL-30B-A3B Instruct	89.5%
247	HRBench 8K O	Hallucination robustness	Hallucination robustness benchmark with 8K token contexts.	★★★★★		🇨🇳 Qwen3-VL-30B-A3B Instruct	82.5%
248	HRM8K o	Korean reasoning	8k-question Korean reasoning and knowledge benchmark.	★★★★★		🇨🇳 Qwen3-235B-A22B-Thinking-2507	92.0%
249	HumanEval O	Code generation	Python synthesis problems evaluated by unit tests.	★★★★★	2916	🇺🇸 Gemini 3 Pro Preview	100.0%
250	HumanEval+ O	Code generation	Extended HumanEval with more tests.	★★★★★	1577	🇺🇸 Claude Sonnet 4	94.5%
251	HumanEval-V o	Code generation (vision)	HumanEval variant with visual programming prompts.	★★★★★		G Step3-VL-10B	66.0%
252	HumanEval-X o	Code generation (multilingual)	Multilingual code generation benchmark extending HumanEval to multiple programming languages.	★★★★★		G TeleChat3-36B-Thinking	92.7%
253	Hypersim O	3D scene understanding	Hypersim benchmark for synthetic indoor scene understanding and reconstruction.	★★★★★		🇺🇸 GPT-5 Mini Minimal	39.3%
254	IFBench O	Instruction following	Instruction-following benchmark measuring compliance and adherence.	★★★★★	70	🇫🇷 Mistral Small 3.2 24B Instruct	84.8%
255	IFEval O	Instruction following	Instruction following capability evaluation for LLMs.	★★★★★	36312	🇺🇸 o3 mini-high	93.9%
256	IFEval-Code o	Instruction following (code)	Instruction following evaluation for code generation tasks.	★★★★★		🇨🇳 Qwen3-32B	28.0%
257	Image QA Average O	Image QA (aggregate)	Average of single-image visual question answering benchmarks.	★★★★★		🇺🇸 Gemini 3 Pro	86.2%
258	IMO AnswerBench O	Math (competition)	Evaluates free-form solutions to International Mathematical Olympiad problems using expert-style grading rubrics.	★★★★★		🇨🇳 LongCat-Flash-Thinking-2601	86.8%
259	INCLUDE O	Inclusiveness / bias	Evaluates inclusive language use and bias mitigation in model outputs.	★★★★★		🇺🇸 Gemini-2.5-Flash Thinking	83.9%
260	InfoQA O	Information-seeking QA	Information retrieval question answering benchmark evaluating factual responses.	★★★★★		🇺🇸 Gemini 3 Pro	86.9%
261	Information Extraction o	Information extraction	Information extraction benchmark for economically valuable fields.	★★★★★		🇺🇸 Claude Sonnet 4.5	46.9%
262	Information Processing o	Information processing	Information processing benchmark for economically valuable tasks.	★★★★★		🇺🇸 Gemini 3 Pro	56.5%
263	InfoVQA O	Infographic VQA	Visual question answering over infographics requiring reading, counting, and reasoning.	★★★★★		🇨🇳 Kimi-K2.5 Thinking	92.6%
264	Intention Recognition o	Intent recognition	Intent recognition benchmark for practical applications.	★★★★★		🇺🇸 Gemini 3 Pro	65.3%
265	IntPhys 2 O	Intuitive physics	Intuitive physics reasoning benchmark.	★★★★★		🇺🇸 Gemini 3 Flash	63.4%
266	Inverse IFEval o	Instruction following (inverse)	Inverse instruction-following evaluation.	★★★★★		🇺🇸 Gemini 3 Pro	80.6%
267	ISL/OSL 8k/16k o	Throughput	Relative throughput on ISL/OSL 8k/16k context workloads.	★★★★★		🇺🇸 Nemotron-3-Nano-30B-A3B	3.3%
268	JudgeMark v2.1 O	LLM judging ability	A benchmark measuring LLM judging ability.	★★★★★		🇺🇸 Claude Sonnet 4	82.0%
269	KGC-Safety o	Safety (Korean)	Korean safety benchmark evaluating harmfulness and compliance.	★★★★★		G K-EXAONE	96.1%
270	KK-4 People o	Working memory (4 people)	Keep/kill working-memory benchmark with 4 people entities.	★★★★★		G K2-V2	92.9%
271	KK-8 People o	Working memory (8 people)	Keep/kill working-memory benchmark with 8 people entities.	★★★★★		G K2-V2	82.8%
272	KMMLU O	Korean knowledge	Korean Massive Multitask Language Understanding benchmark.	★★★★★		🇨🇳 DeepSeek V3.1	78.7%
273	KMMLU-Pro O	Multilingual knowledge	Korean Multilingual Massive Multitask Language Understanding Pro	★★★★★		🇺🇸 o1	77.5%
274	KMMLU-Redux O	Multilingual knowledge	Redux variant of KMMLU benchmark	★★★★★		🇺🇸 o1	81.1%
275	Ko-LongBench o	Korean long-context	Long-context understanding benchmark in Korean.	★★★★★		🇨🇳 DeepSeek V3.2-Thinking	87.9%
276	KoBALT o	Korean knowledge	Korean benchmark for knowledge and language understanding.	★★★★★		🇨🇳 DeepSeek V3.2-Thinking	62.7%
277	KoMT-Bench o	Korean chat ability	Korean multi-turn chat evaluation benchmark.	★★★★★		🇨🇳 Qwen3-30B-A3B-Instruct-2507	8.5%
278	KOR-Bench O	Reasoning	Comprehensive reasoning benchmark spanning diverse domains and cognitive skills.	★★★★★		🇺🇸 GPT-5 High	77.4%
279	KoSimpleQA o	Korean QA	Korean simple question answering benchmark.	★★★★★		G Kanana-2-30B-A3B-Mid-2601	49.7%
280	KSM o	Multilingual math	Korean STEM and math benchmark	★★★★★		G EXAONE Deep 2.4B	60.9%
281	LAMBADA O	Language modeling	Word prediction requiring broad context understanding.	★★★★★		🇺🇸 GPT-3	86.4%
282	LatentJailbreak o	Safety / jailbreak	Robustness to latent jailbreak adversarial techniques.	★★★★★	39	🇺🇸 GPT-3.5-turbo	77.4%
283	LBV1-QA O	Vision-language	Vision-language QA benchmark v1.	★★★★★		🇺🇸 GPT-5	73.7%
284	LBV2 O	Vision-language	Vision-language benchmark v2.	★★★★★		🇺🇸 Gemini 2.5 Pro	65.7%
285	LiveBench O	General capability	Continually updated capability benchmark across diverse tasks.	★★★★★		🇺🇸 Gemini 2.5 Pro	82.4%
286	LiveCodeBench O	Code generation	Live coding and execution-based evaluation benchmark (v6 dataset).	★★★★★		🇺🇸 Gemini 3 Pro	92.0%
287	LiveCodeBench-Ko o	Code generation (Korean)	Korean translation of LiveCodeBench.	★★★★★		🇨🇳 Qwen3-30B-A3B-Thinking-2507	66.3%
288	LiveCodeBench Pro O	Competitive coding problems from Codeforces, ICPC, and IOI	LiveCodeBench Pro evaluates competitive programming performance across Codeforces, ICPC, and IOI contests. Elo rating, higher is better.	★★★★★		🇺🇸 Gemini 3 Pro	2439
289	LCB Pro 25Q2 (Easy) o	Code generation	LiveCodeBench Pro 2025 Q2 easy subset.	★★★★★		🇺🇸 Nemotron-Cascade-14B-Thinking	68.9%
290	LCB Pro 25Q2 (Med) O	Code generation	LiveCodeBench Pro 2025 Q2 medium subset.	★★★★★		🇺🇸 GPT-OSS 120B (High)	35.4%
291	LiveCodeBench v3 O	Code generation	LiveCodeBench v3 snapshot measuring pass rates on streaming coding tasks.	★★★★★		🇨🇳 Qwen3 32B	90.2%
292	LiveCodeBench v5 (2024.10-2025.02) O	Code generation	LiveCodeBench v5 snapshot covering Oct 2024-Feb 2025.	★★★★★		G IQuest-Coder-V1-40B-Loop-Thinking	86.2%
293	LiveMCP-101 O	Agent real-time eval	A novel real-time evaluation framework and benchmark to stress‑test agents on complex, real‑world tasks.	★★★★★		🇺🇸 GPT-5	58.4%
294	LiveSports-3K o	Sports video	Live sports video understanding benchmark (3K).	★★★★★		G Seed1.8	77.5%
295	LMArena Text O	Crowd eval (text)	Chatbot Arena text evaluation (average win rate).	★★★★★		🇺🇸 Gemini 2.5 Pro	1455
296	LMArena Vision O	Crowd eval (vision)	Chatbot Arena vision evaluation leaderboard (ELO ratings).	★★★★★		🇺🇸 Gemini 2.5 Pro	1242
297	LogicVista O	Visual logical reasoning	Visual logic and pattern reasoning tasks requiring compositional and spatial understanding.	★★★★★		🇺🇸 Gemini 3 Pro	80.8%
298	LogiQA o	Logical reasoning	Reading comprehension with logical reasoning.	★★★★★	138	G Pythia 70M	23.5%
299	LongBench o	Long-context eval	Long-context understanding across tasks.	★★★★★	957	G Jamba Mini 1.6	32.0%
300	longbench-v2 O	Long-context eval	Next-generation LongBench v2 long-context evaluation benchmark.	★★★★★		🇺🇸 Gemini 3 Pro	68.2%
301	LongFact-Concepts o	Hallucination rate on open-source prompts	Long-context factuality eval focused on conceptual statements; lower is better.	★★★★★		🇺🇸 GPT-5	↓ 0.7%
302	LongFact-Objects o	Hallucination rate on open-source prompts	Long-context factuality eval focused on object/entity references; lower is better.	★★★★★		🇺🇸 GPT-5	↓ 0.8%
303	LongText-Bench EN o	Text rendering	LongText-Bench English subset score for text rendering.	★★★★★		G Seedream 4.5	1.0%
304	LongText-Bench ZH o	Text rendering	LongText-Bench Chinese subset score for text rendering.	★★★★★		G Seedream 4.5	1.0%
305	LongVideoBench o	Long video QA	Long video understanding and QA benchmark.	★★★★★		🇨🇳 Kimi-K2.5 Thinking	79.8%
306	LPFQA o	Finance QA	Long-form financial question answering benchmark.	★★★★★		🇺🇸 GPT-5 High	54.4%
307	LVBench O	Video understanding	Long video understanding benchmark (LVBench).	★★★★★		🇨🇳 Kimi-K2.5 Thinking	75.9%
308	M3GIA (CN) o	Chinese multimodal QA	Chinese-language M3GIA benchmark covering grounded multimodal question answering.	★★★★★		🇨🇳 Seed1.5-VL-Thinking	91.2%
309	Machiavelli O	Deception / safety	Benchmark for deceptive or manipulative behavior in social interactions.	★★★★★		🇺🇸 Claude Haiku 4.5	↓ 52.2%
310	MakeMeSay o	Adversarial robustness	Adversarial benchmark testing model robustness against manipulation attempts. Lower is better.	★★★★★		🇺🇸 Grok 4.1 (Thinking)
311	Mantis O	Multimodal reasoning	Multimodal reasoning and instruction following benchmark (Mantis).	★★★★★		G dots.vlm1	86.2%
312	MARS-Bench o	Instruction following	Instruction-following benchmark with complex tasks.	★★★★★		🇺🇸 Gemini 3 Pro	80.8%
313	MASK O	Safety / red teaming	Model behavior safety assessment via red-teaming scenarios.	★★★★★		🇺🇸 Claude Sonnet 4 (t)	95.3%
314	MATH O	Math (competition)	Competition-level mathematics across algebra, geometry, number theory, combinatorics.	★★★★★	1185	🇺🇸 o3 mini	97.9%
315	MATH-Ko o	Math (Korean)	Korean translation of the MATH competition benchmark.	★★★★★		🇨🇳 Qwen3-30B-A3B	58.2%
316	MATH Level 5 o	Math (competition)	Level 5 subset of the MATH benchmark emphasizing the hardest competition-style problems.	★★★★★		🇨🇳 Qwen3-4B-Instruct-2507	73.6%
317	MATH500 O	Math reasoning	500-problem slice of the MATH benchmark for challenging math reasoning.	★★★★★		G Motif-2-12.7B-Reasoning	99.3%
318	MATH500 (ES) o	Math (multilingual)	Spanish MATH500 benchmark	★★★★★		G EXAONE 4.0 1.2B	88.8%
319	MathArena Apex o	Challenging Math Contest problems	Challenging math contest problems from MathArena Apex benchmark.	★★★★★		🇺🇸 Gemini 3 Pro	23.4%
320	MathVerse-mini O	Math reasoning (multimodal)	Compact MathVerse split focusing on single-image math puzzles and visual reasoning.	★★★★★		🇨🇳 Qwen3-VL-235B-A22B Thinking	85.0%
321	MathVerse-Vision O	Math reasoning (multimodal)	Multi-image visual mathematical reasoning tasks from the MathVerse ecosystem.	★★★★★		🇺🇸 GPT-5 High	84.1%
322	MathVision O	Math reasoning (multimodal)	Visual math reasoning benchmark with problems that combine images (charts, diagrams) and text.	★★★★★		🇺🇸 Gemini 3 Pro	86.1%
323	MathVista O	Multimodal math reasoning	Visual math reasoning across diverse tasks.	★★★★★		🇨🇳 Kimi-K2.5 Thinking	90.1%
324	MathVista-Mini O	Math reasoning (multimodal)	Lightweight subset of MathVista for quick evaluation of visual mathematical reasoning.	★★★★★		🇨🇳 Qwen3-VL-235B-A22B Thinking	85.8%
325	MBPP O	Code generation	Short Python problems with hidden tests.	★★★★★	36312	🇨🇳 Kimi-K2 Thinking	97.4%
326	MBPP-Ko o	Code generation (Korean)	Korean translation of MBPP code generation benchmark.	★★★★★		🇨🇳 Qwen3-30B-A3B	66.8%
327	MBPP+ O	Code generation	Extended MBPP with more tests and stricter evaluation.	★★★★★		🇨🇳 GLM 4.6	94.2%
328	MCP-Atlas O	Agent evaluation	Aggregate MCP agent benchmark covering tool-use and planning tasks.	★★★★★		🇺🇸 Claude Opus 4.5	62.3%
329	MCP Universe O	Agent evaluation	Benchmarks multi-step tool-use agents across diverse task suites with a unified overall success metric.	★★★★★		🇺🇸 Gemini 3 Pro	50.7%
330	MCPMark O	Agent tool-use (MCP)	Benchmark for Model Context Protocol (MCP) agent tool-use.	★★★★★	127	🇺🇸 GPT-5 High	50.9%
331	METR O	Long task benchmark	METR evaluates AI agents on long-horizon coding and agentic tasks, measuring autonomous task completion time.	★★★★★		🇺🇸 Claude Opus 4.5	4.8%
332	MGSM O	Math (multilingual)	Multilingual grade school math word problems.	★★★★★		🇺🇸 Claude Opus 4.1 (2025-08-05) Thinking	94.4%
333	MIABench O	Multimodal instruction following	Multimodal instruction-following benchmark evaluating accuracy on complex image-text tasks.	★★★★★		🇨🇳 Qwen3-VL-235B-A22B Thinking	92.7%
334	NIAH-Multi 128K o	Long-context QA	Needle-in-a-haystack multi-query benchmark at 128K context.	★★★★★		🇨🇳 Kimi-K2 Base	99.5%
335	NIAH-Multi 32K o	Long-context QA	Needle-in-a-haystack multi-query benchmark at 32K context.	★★★★★		🇨🇳 Kimi-K2 Base	99.8%
336	NIAH-Multi 64K o	Long-context QA	Needle-in-a-haystack multi-query benchmark at 64K context.	★★★★★		🇨🇳 Kimi-K2 Base	100.0%
337	MindCube O	Spatial navigation	Spatial navigation benchmark.	★★★★★		🇺🇸 Gemini 3 Flash	78.3%
338	Minerva Math O	University-level math	Advanced quantitative reasoning set inspired by the Minerva benchmark for STEM problem solving.	★★★★★		🇨🇳 Qwen3 235B A22B Thinking	98.0%
339	MiniF2F pass@1 o	Math competition	MiniF2F competition benchmark pass@1 accuracy.	★★★★★		🇺🇸 NVIDIA-Nemotron-3-Nano-30B-A3B-BF16	50.0%
340	MiniF2F pass@32 o	Math competition	MiniF2F competition benchmark pass@32 accuracy.	★★★★★		🇺🇸 NVIDIA-Nemotron-3-Nano-30B-A3B-BF16	79.9%
341	MiniF2F (Test) o	Math competition	MiniF2F competition benchmark (test split).	★★★★★		🇨🇳 LongCat-Flash-Thinking	81.6%
342	MixEval o	Multi-task reasoning	Mixed-subject benchmark covering knowledge and reasoning tasks across domains.	★★★★★		🇺🇸 o1 Mini	82.9%
343	MixEval Hard o	Multi-task reasoning (hard)	Hard subset of MixEval covering diverse reasoning tasks.	★★★★★		🇨🇳 Qwen3-4B	31.6%
344	MLVU O	Large video understanding	MLVU: Large-scale multi-task benchmark for video understanding.	★★★★★		🇺🇸 GPT-5	86.2%
345	MM-BrowseComp o	Multimodal browsing	Multimodal browsing comprehension benchmark.	★★★★★		G Seed1.8	46.3%
346	MM-IFEval o	Multimodal instruction following	Instruction-following benchmark assessing multimodal obedience to complex prompts.	★★★★★		🇺🇸 LFM2.5-VL-1.6B	52.3%
347	MM-MT-Bench O	Multimodal instruction following	Multi-turn multimodal instruction following benchmark evaluating dialogue quality and helpfulness.	★★★★★		🇨🇳 Qwen3-VL-235B-A22B Thinking	8.5%
348	MMBench v1.1 (CN) O	Multimodal understanding (Chinese)	MMBench v1.1 Chinese subset for evaluating multimodal LLMs.	★★★★★		🇺🇸 Gemini 3 Pro	91.3%
349	MMBench v1.1 (EN) O	Multimodal understanding (English)	MMBench v1.1 English subset for evaluating multimodal LLMs.	★★★★★		🇺🇸 Gemini 3 Pro	93.3%
350	MMBench v1.1 (EN dev) O	General VQA	English dev split of MMBench v1.1 measuring multimodal question answering.	★★★★★		🇨🇳 Qwen3-VL-235B-A22B Thinking	90.6%
351	MME-CC o	Multimodal evaluation	MME-CC multimodal evaluation suite.	★★★★★		🇺🇸 Gemini 3 Pro	56.9%
352	MME Elo o	Multimodal perception	Elo-style scoring for the MME multimodal evaluation benchmark.	★★★★★		🇨🇳 InternVL3-2B	2186.4%
353	MME-RealWorld (cn) o	Real-world perception (CN)	MME-RealWorld Chinese split.	★★★★★		🇺🇸 GPT-4o	58.5%
354	MME-RealWorld (en) o	Real-world perception (EN)	MME-RealWorld English split.	★★★★★		G MiMo-VL 7B-RL	59.1%
355	MMIU O	Multi-image understanding	Multi-image understanding benchmark evaluating cross-image reasoning.	★★★★★		🇺🇸 Gemini 3 Pro	72.1%
356	MMLB-NIAH (128k) o	Multimodal long-context	MMLB-NIAH 128k long-context multimodal benchmark.	★★★★★		G Seed1.8	72.2%
357	MMLB-VRAG (128k) o	Multimodal long-context	MMLB-VRAG 128k long-context multimodal benchmark.	★★★★★		🇺🇸 Gemini 3 Pro	88.9%
358	MMLongBench-128K o	Long-context multimodal	128K-context variant of MMLongBench evaluating multimodal long-context understanding.	★★★★★		🇨🇳 GLM-4.6V	64.1%
359	MMLongBench-Doc O	Long-context multimodal documents	Evaluates long-context document understanding with mixed text, tables, and figures across multiple pages.	★★★★★		🇨🇳 Qwen3-VL-235B-A22B Thinking	56.2%
360	MMLU O	Multi-domain knowledge	57 tasks spanning STEM, humanities, social sciences; broad knowledge and reasoning.	★★★★★	1488	🇺🇸 GPT-5 High	93.8%
361	MMLU Arabic o	Arabic knowledge and reasoning	Arabic-language variant of MMLU evaluating knowledge and reasoning.	★★★★★		🇨🇳 Qwen 2.5 72B	74.1%
362	MMLU (cloze) o	Multi-domain knowledge (cloze)	Cloze-form MMLU evaluation variant.	★★★★★		🇺🇸 SmolLM2 135M Base	31.5%
363	Full Text MMLU o	Multi-domain knowledge (long-form)	Full-context MMLU variant evaluating reasoning over long passages.	★★★★★		🇺🇸 Llama 3.3 70B Instruct	83.0%
364	MMLU-Pro O	Multi-domain knowledge	Harder successor to MMLU with more challenging questions.	★★★★★	286	🇺🇸 Gemini 3 Pro	90.1%
365	MMLU Pro MCF o	Multi-domain knowledge (few-shot)	MMLU-Pro common format (MCF) few-shot evaluation.	★★★★★		🇨🇳 Qwen3-4B-Base	41.1%
366	MMLU-ProX O	Multi-domain knowledge	Cross-lingual and robust variant of MMLU-Pro.	★★★★★		🇨🇳 Qwen3-235B-A22B-Thinking-2507	81.0%
367	MMLU-Redux O	Multi-domain knowledge	Updated MMLU-style evaluation with revised questions and scoring.	★★★★★		🇺🇸 Gemini 3 Pro	95.9%
368	MMLU-STEM O	STEM knowledge	STEM subset of MMLU.	★★★★★	1488	G Falcon-H1-34B-Instruct	83.6%
369	MMMB o	Multilingual MMBench	Multilingual Multimodal Benchmark (MMMB) average score.	★★★★★		🇺🇸 LFM2.5-VL-1.6B	77.0%
370	MMMLU O	Multi-domain knowledge (multilingual)	Massively multilingual MMLU-style evaluation across many languages.	★★★★★		🇺🇸 Gemini 3 Pro	91.8%
371	MMMLU (ES) o	Multilingual knowledge	Spanish MMMLU benchmark	★★★★★		🇺🇸 SmolLM 3 3B	64.7%
372	MMMU O	Multimodal understanding	Multi-discipline multimodal understanding benchmark.	★★★★★		🇺🇸 Gemini 3 Pro	87.0%
373	MMMU PRO O	Multimodal understanding (hard)	Professional/advanced subset of MMMU for multimodal reasoning.	★★★★★		🇺🇸 Gemini 3 Flash	81.2%
374	MMMU-Pro (vision) o	Multimodal understanding (vision)	MMMU-Pro vision-only setting.	★★★★★		🇺🇸 Claude 3.7 Sonnet	45.8%
375	MMSIBench (circular) o	Spatial understanding	MMSIBench circular subset for spatial reasoning.	★★★★★		🇺🇸 Gemini 3 Pro	25.4%
376	MMStar O	Multimodal reasoning	Broad evaluation of multimodal LLMs across diverse tasks.	★★★★★		🇺🇸 Gemini 3 Pro	83.1%
377	MMVP O	Multimodal video perception	Benchmark for multimodal video understanding and perception.	★★★★★		G Seed1.8	91.6%
378	MMVU O	Video understanding	Multimodal video understanding benchmark (MMVU).	★★★★★		🇺🇸 GPT-5.2 Thinking XHigh	80.8%
379	MotionBench O	Video motion understanding	Video motion and temporal reasoning benchmark.	★★★★★		G Seed1.8	70.6%
380	OpenAI-MRCR (128k) O	Long-context reasoning	OpenAI Multi-Round Chain Reasoning benchmark with 128k context window.	★★★★★		🇺🇸 Gemini 3 Pro	89.7%
381	OpenAI-MRCR (1M) o	Long-context reasoning	OpenAI Multi-Round Chain Reasoning benchmark with 1M context window.	★★★★★		🇺🇸 Gemini 2.5 Pro	58.8%
382	MRCR v2 o	Multimodal reasoning	Multi-round multimodal chain-of-reasoning evaluation (v2).	★★★★★		🇺🇸 Gemini 2.5 Flash	81.7%
383	MT-Bench O	Chat ability	Multi-turn chat evaluation via GPT-4 grading.	★★★★★	39074	🇺🇸 Apriel Nemotron 15B Thinker	85.7%
384	MTOB (full book) o	Long-form reasoning	Long-context book understanding benchmark (full-book setting).	★★★★★		🇺🇸 Llama 4 Maverick	50.8%
385	MTOB (half book) o	Long-form reasoning	Long-context book understanding benchmark (half-book setting).	★★★★★		🇺🇸 Llama 4 Maverick	54.0%
386	MUIRBENCH O	Multimodal robustness	Evaluates multimodal understanding robustness and reliability.	★★★★★		🇺🇸 Gemini 3 Pro	86.1%
387	Multi-IF O	Instruction following (multi-task)	Composite instruction-following evaluation across multiple tasks.	★★★★★		🇨🇳 Qwen3-30B-A3B	81.0%
388	Multi-IFEval O	Instruction following (multi-task)	Multi-task variant of instruction-following evaluation.	★★★★★		🇺🇸 Llama 3.3 70B	88.7%
389	Multi-SWE-Bench O	Code repair (multi-repo)	Multi-repository SWE-Bench variant.	★★★★★	246	G MiniMax M2.1	49.4%
390	MultiChallenge O	Instruction following	Multi-domain instruction-following benchmark.	★★★★★		🇺🇸 GPT-5	69.6%
391	Multi-Image QA Average O	Multi-image QA (aggregate)	Aggregate score over multi-image visual question answering tasks.	★★★★★		🇺🇸 Gemini 3 Pro	81.9%
392	Multilingual MMBench o	Multilingual vision benchmark	Multilingual MMBench average score across languages.	★★★★★		🇺🇸 LFM2.5-VL-1.6B	65.9%
393	Multilingual MMLU O	Multi-domain knowledge (multilingual)	Multilingual variant of MMLU across many languages.	★★★★★		🇺🇸 GPT-4.1	87.3%
394	MultiPL-E O	Code generation (multilingual)	Multilingual code generation and execution benchmark across many programming languages.	★★★★★	269	🇺🇸 Claude Opus 4	89.6%
395	MultiPL-E HumanEval o	Code generation (multilingual)	MultiPL-E variant of HumanEval tasks.	★★★★★		🇺🇸 Llama 3.1 405B	75.2%
396	MultiPL-E MBPP o	Code generation (multilingual)	MultiPL-E variant of MBPP tasks.	★★★★★		🇺🇸 Llama 3.1 405B	65.7%
397	MuSR O	Reasoning	Multistep Soft Reasoning.	★★★★★		🇺🇸 Hermes 4.3 70B	70.4%
398	MVBench O	Video QA	Multi-view or multi-video QA benchmark (MVBench).	★★★★★		🇨🇳 GLM-4.5V	73.0%
399	Natural2Code o	Code generation	Natural language to code benchmark for instruction-following synthesis.	★★★★★		🇺🇸 Gemini 2.0 Flash	92.9%
400	NaturalQuestions O	Open-domain QA	Google NQ; real user questions with long/short answers.	★★★★★		🇫🇷 Mixtral 8x22B	40.1%
401	Nexus (0-shot) o	Tool use	Nexus tool-use benchmark, zero-shot setting.	★★★★★		🇺🇸 Llama 3.1 405B	58.7%
402	Needle In A Haystack o	Long-context retrieval	Needle In A Haystack test for locating hidden facts in long contexts.	★★★★★		G MobileLLM P1 Base	100.0%
403	Objectron o	Object detection	Objectron benchmark for 3D object detection in video captures.	★★★★★		🇨🇳 Qwen3-VL-235B-A22B Thinking	71.2%
404	OBQA o	Open book QA	OpenBookQA science question answering benchmark.	★★★★★		🇨🇳 Qwen2.5-Omni-3B	76.3%
405	OCRBench V2 O	OCR (vision text extraction)	OCRBench v2 evaluating text extraction from images and documents.	★★★★★		🇨🇳 Qwen3-VL 2B Instruct	858.0%
406	OCRBench-ELO o	OCR (ELO ranking)	OCR benchmark using ELO rating system to rank model performance on text extraction tasks.	★★★★★		🇺🇸 Gemini 2.5 Pro	866
407	OCRBenchV2 (CN) O	OCR (Chinese)	OCRBenchV2 Chinese subset assessing OCR performance on Chinese-language documents.	★★★★★		🇨🇳 Qwen2.5-VL 72B Instruct	63.7%
408	OCRBenchV2 (EN) O	OCR (English)	OCRBenchV2 English subset evaluating OCR accuracy on English documents and layouts.	★★★★★		🇨🇳 Qwen3-VL 32B Instruct	67.4%
409	OCRReasoning o	OCR reasoning	OCR reasoning benchmark combining text extraction with multi-step reasoning over documents.	★★★★★		🇺🇸 Gemini 2.5 Pro	70.8%
410	OctoCodingBench o	Code generation	Coding benchmark across multi-language programming tasks.	★★★★★		🇺🇸 Claude Opus 4.5	36.2%
411	ODinW-13 O	Object detection (in the wild)	Object Detection in the Wild benchmark covering 13 real-world domains.	★★★★★		🇨🇳 Qwen3-VL-4B-Instruct	48.2%
412	Odyssey Math o	Math reasoning	Odyssey multi-step math benchmark.	★★★★★		G Mathstral 7B	37.2%
413	OIBench EN o	Code generation	English subset of OIBench for code generation.	★★★★★		🇺🇸 Gemini 3 Pro	58.2%
414	OJBench O	Code generation (online judge)	Programming problems evaluated via online judge-style execution.	★★★★★		🇺🇸 Gemini 3 Pro	68.5%
415	olmOCR-Bench O	Document OCR	olmOCR benchmark assessing OCR fidelity and structured extraction on complex document pages.	★★★★★		G Chandra OCR 0.1.0	83.1%
416	OlympiadBench o	Math (olympiad)	Advanced mathematics olympiad-style problem benchmark.	★★★★★		🇨🇳 Qwen3-30B-A3B-Instruct-2507	77.6%
417	OlympicArena o	Math (competition)	Olympiad-style mathematics reasoning benchmark.	★★★★★		🇨🇳 DeepSeek V3	76.2%
418	OMEGA O	Math (advanced)	OMEGA olympiad-grade mathematics reasoning benchmark.	★★★★★		🇺🇸 OLMo-3-Think-32B	50.8%
419	Omni-MATH O	Math reasoning	Omni-MATH benchmark covering diverse math reasoning tasks across difficulty levels.	★★★★★		G Ling 1T	74.5%
420	Omni-MATH-HARD O	Math	Challenging math benchmark (Omni-MATH-HARD).	★★★★★		🇺🇸 GPT-5 High	73.6%
421	OmniDocBench O	Document understanding	Document understanding benchmark covering multi-page layouts, tables, and charts for robust question answering.	★★★★★		G Gundam-M	↓ 12.3%
422	OmniDocBench 1.5 O	OCR	Document understanding benchmark v1.5 with OCR evaluation. Overall Edit Distance metric, lower is better.	★★★★★		🇺🇸 Dolphin V2	↓ 0.1%
423	OmniDocBench-CN O	Document understanding (Chinese)	Chinese subset of OmniDocBench focusing on OCR-grounded document comprehension and reasoning.	★★★★★		G PPStructure v3	↓ 13.6%
424	OmniMMI o	Multimodal interaction	OmniMMI benchmark for multimodal interaction across video streams.	★★★★★		G Seed1.8	53.0%
425	OmniSpatial o	Spatial reasoning	Spatial understanding and reasoning benchmark (OmniSpatial).	★★★★★		🇨🇳 GLM-4.6V	52.0%
426	OneIG-Bench EN O	Text-to-image	OneIG-Bench English subset score for text-to-image generation.	★★★★★		G Nano Banana 2.0	0.6%
427	OneIG-Bench ZH O	Text-to-image	OneIG-Bench Chinese subset score for text-to-image generation.	★★★★★		G Nano Banana 2.0	0.6%
428	Online-Mind2web o	Web automation	Online web automation and task execution benchmark.	★★★★★		G Seed1.8	85.9%
429	Open Rewrite o	Instruction following	Rewrite benchmark assessing open-ended editing and directive-following quality.	★★★★★		G MobileLLM P1	51.0%
430	OpenBookQA O	Science QA	Open-book multiple choice science questions with supporting facts.	★★★★★	128	🇺🇸 Hermes 4.3 36B Pyche	96.6%
431	OpenRewrite-Eval o	Rewrite quality	OpenRewrite evaluation; micro-averaged RougeL.	★★★★★		🇨🇳 Qwen2.5 1.5B Instruct	46.9%
432	OptMATH o	Math optimization reasoning	OptMATH benchmark targeting challenging math optimization and problem-solving tasks.	★★★★★		G Ling 1T	57.7%
433	Order 15 Items o	List ordering	Ordering benchmark requiring models to sequence 15 items correctly.	★★★★★		G K2-V2	87.6%
434	Order 30 Items o	List ordering (long)	Ordering benchmark requiring models to sequence 30 items correctly.	★★★★★		G K2-V2	40.3%
435	OSWorld O	GUI agents	Agentic GUI task completion and grounding on desktop environments.	★★★★★		🇺🇸 Claude Opus 4.5	66.3%
436	OSWorld-G O	GUI agents	OSWorld-G center accuracy (no_refusal).	★★★★★		🇺🇸 Holo1.5-72B	71.8%
437	OSWorld2 o	GUI agents	Second-generation OSWorld GUI agent benchmark.	★★★★★		🇨🇳 GLM-4.5V	35.8%
438	OVBench o	Open-vocabulary streaming	Open-vocabulary benchmark for streaming video understanding.	★★★★★		G Seed1.8	65.1%
439	OVOBench o	Streaming video QA	Streaming video QA benchmark with open-vocabulary queries.	★★★★★		G Seed1.8	72.6%
440	PaperBench Code-Dev o	Code understanding	PaperBench developer subset measuring code reasoning accuracy.	★★★★★		🇺🇸 Claude Sonnet 4	43.3%
441	PaperBench o	Research paper understanding	Benchmark for understanding and reasoning over research papers.	★★★★★		🇺🇸 Claude Opus 4.5 Thinking	72.9%
442	PHYBench o	Physics reasoning	Physics reasoning and calculation benchmark.	★★★★★		🇺🇸 Gemini 3 Pro	59.0%
443	PhyX o	Physics reasoning (multimodal)	Multimodal physics reasoning benchmark (PhyX).	★★★★★		G Step3-VL-10B	59.5%
444	PIQA O	Physical commonsense	Physical commonsense about everyday tasks and object affordances.	★★★★★		🇨🇳 GLM-4.5 Base	87.1%
445	PixmoCount O	Visual counting	Counting objects/instances in images (PixmoCount).	★★★★★		G Eagle2.5-8B	90.2%
446	Point-Bench o	Pointing and counting	Benchmark for pointing and counting objects in images.	★★★★★		🇺🇸 Gemini 2.5 Pro	85.5%
447	PolyMATH O	Math reasoning	Polyglot mathematics benchmark assessing cross-topic math reasoning.	★★★★★		🇨🇳 Kimi K2 Instruct	65.1%
448	POPE o	Hallucination detection	Vision-language hallucination benchmark focusing on object existence verification.	★★★★★		🇨🇳 InternVL3-2B	90.1%
449	PopQA O	Knowledge / QA	Open-domain popular culture question answering benchmark testing long-tail factual recall.	★★★★★		🇺🇸 Llama 3.1 Tulu 3 405B SFT	55.7%
450	PostTrainBench o	Post-training automation	Measures how well AI agents can post-train base LLMs under fixed compute/time constraints; average score across AIME 2025, BFCL, GPQA Main, GSM8K, and HumanEval.	★★★★★		🇺🇸 GPT-5.1 Codex-Max	34.9%
451	ProofBench Advanced o	Mathematical proofs (advanced)	Advanced mathematical proof benchmark covering complex theorem proving tasks.	★★★★★		🇺🇸 Gemini Deep Think (IMO Gold)	65.7%
452	ProofBench Basic o	Mathematical proofs	Entry-level mathematical proof benchmarking set.	★★★★★		🇨🇳 DeepSeekMath-V2-Heavy	99.0%
453	ProtocolQA o	Protocol understanding and QA	Protocol question answering benchmark evaluating understanding of scientific protocols and procedures.	★★★★★		🇺🇸 Grok 4.1 (Thinking)	79.0%
454	QuAC o	Conversational QA	Question answering in context.	★★★★★		🇺🇸 Llama 3.1 405B Base	53.6%
455	QuALITY o	Long-context reading comprehension	Long-document multiple-choice reading comprehension benchmark.	★★★★★		🇺🇸 Llama-3_1-70B-TFree-HAT-SFT	48.8%
456	RACE o	Reading comprehension	English exams for middle and high school.	★★★★★		🇺🇸 Nemotron-3-Nano-30B-A3B-Base	88.0%
457	Random Complex Tasks o	Agentic tasks (random)	Randomly constructed complex task environments for agent generalization.	★★★★★		🇨🇳 LongCat-Flash-Thinking-2601	35.8%
458	Realbench o	Web browsing	Real-world browsing and QA benchmark.	★★★★★		G Seed1.8	49.1%
459	RealWorldQA O	Real-world visual QA	Visual question answering with real-world images and scenarios.	★★★★★		🇺🇸 GPT-5	82.8%
460	Ref-L4 (test) o	Referring expressions	Ref-L4 referring expression comprehension on the test split.	★★★★★		🇨🇳 GLM-4.6V	88.9%
461	RefCOCO O	Referring expressions	RefCOCO average accuracy at IoU 0.5 (val).	★★★★★		🇨🇳 InternVL3.5-4B	92.4%
462	RefCOCOg o	Referring expressions	RefCOCOg average accuracy at IoU 0.5 (val).	★★★★★		G Moondream-9B-A2B	88.6%
463	RefCOCO+ o	Referring expressions	RefCOCO+ accuracy at IoU 0.5 on the val split.	★★★★★		G Moondream-9B-A2B	81.8%
464	RefSpatialBench O	Spatial reasoning	Reference spatial understanding benchmark covering spatial grounding tasks.	★★★★★		🇨🇳 Qwen2.5-VL 72B Instruct	72.1%
465	RefusalBench o	Safety / refusal	Safety-oriented refusal and policy adherence benchmark.	★★★★★		🇺🇸 Hermes 4.3 36B Pyche	72.3%
466	ReMI o	Multimodal reasoning	Reasoning over multimodal inputs (ReMI).	★★★★★		G Step3-VL-10B	67.3%
467	RepoBench O	Code understanding	Repository-level code comprehension and reasoning benchmark.	★★★★★		🇺🇸 Claude Sonnet 4.5	83.8%
468	RoboSpatialHome O	Embodied spatial understanding	RoboSpatialHome benchmark for embodied spatial reasoning in domestic environments.	★★★★★		🇨🇳 Qwen3-VL-235B-A22B Thinking	73.9%
469	Roo Code Evals O	Code assistant eval	Community-maintained coding evals and leaderboard by Roo Code.	★★★★★		🇺🇸 GPT-5 mini	99.0%
470	RULER-100 @1M o	Long-context eval	RULER-100 evaluation at a 1M context window.	★★★★★		🇺🇸 NVIDIA-Nemotron-3-Nano-30B-A3B-BF16	86.3%
471	RULER-100 @256k o	Long-context eval	RULER-100 evaluation at a 256k context window.	★★★★★		🇺🇸 NVIDIA-Nemotron-3-Nano-30B-A3B-BF16	92.9%
472	RULER-100 @512k o	Long-context eval	RULER-100 evaluation at a 512k context window.	★★★★★		🇺🇸 NVIDIA-Nemotron-3-Nano-30B-A3B-BF16	91.3%
473	Ruler 128k o	Long-context eval	RULER benchmark at 128k context window.	★★★★★		🇨🇳 Kimi-Linear-Instruct	95.4%
474	Ruler 16k o	Long-context eval	RULER benchmark at 16k context window.	★★★★★		🇨🇳 Qwen2.5 7.6B	92.2%
475	Ruler 1M o	Long-context eval	RULER benchmark at 1M context window.	★★★★★		🇨🇳 Kimi-Linear-Instruct	94.8%
476	Ruler 32k o	Long-context eval	RULER benchmark at 32k context window.	★★★★★		🇫🇷 Mistral Medium 3	96.0%
477	Ruler 4k o	Long-context eval	RULER benchmark at 4k context window.	★★★★★		🇫🇷 Ministral 8B	96.0%
478	Ruler 64k o	Long-context eval	RULER benchmark at 64k context window.	★★★★★		🇺🇸 Nemotron-3-Nano-30B-A3B-Base	87.5%
479	Ruler 8k o	Long-context eval	RULER benchmark at 8k context window.	★★★★★		🇺🇸 Llama 3.1 8B Base	93.8%
480	RW Search o	Agentic search	Real-world search benchmark evaluating retrieval and reasoning.	★★★★★		🇺🇸 GPT-5.2 Thinking XHigh	82.0%
481	SALAD-Bench o	Safety alignment	Safety Alignment and Dangerous-behavior benchmark evaluating harmful assistance and refusal consistency.	★★★★★		G Granite-4.0-H-Micro	↓ 96.8%
482	Scale AI Multi Challenge o	Chat & instruction following	Scale AI Multi Challenge crowd-evaluated instruction following benchmark.	★★★★★		🇨🇳 Qwen3-30B-A3B-Thinking-2507	44.8%
483	SciCode (sub) O	Code	SciCode subset score (sub).	★★★★★		🇺🇸 Gemini 3 Pro	56.1%
484	SciCode (main) O	Code	SciCode main score.	★★★★★		🇺🇸 Gemini 2.5 Pro	15.4%
485	ScienceQA O	Science QA (multimodal)	Multiple-choice science questions with images, diagrams, and text context.	★★★★★		G FastVLM-7B	96.7%
486	SciQ o	Science QA	Multiple choice science questions.	★★★★★		G Pythia 12B	92.9%
487	SciRes FrontierMath Tier 1-3 o	Math (frontier)	SciRes FrontierMath benchmark covering tiers 1-3.	★★★★★		🇺🇸 GPT-5.2 Thinking	40.3%
488	SciRes FrontierMath Tier 4 o	Math (frontier)	SciRes FrontierMath benchmark covering tier 4.	★★★★★		🇺🇸 Gemini 3 Pro	18.8%
489	ScreenQA Complex O	GUI QA	Complex ScreenQA benchmark accuracy.	★★★★★		🇺🇸 Holo1.5-72B	87.1%
490	ScreenQA Short O	GUI QA	Short-form ScreenQA benchmark accuracy.	★★★★★		🇺🇸 Holo1.5-72B	91.9%
491	ScreenSpot O	Screen UI locators	Center accuracy on ScreenSpot.	★★★★★		🇨🇳 Qwen3-VL 32B Instruct	95.8%
492	ScreenSpot-Pro O	Screen UI locators	Average center accuracy on ScreenSpot-Pro.	★★★★★		🇺🇸 GPT-5.2 Extra High	86.3%
493	ScreenSpot-v2 O	Screen UI locators	Center accuracy on ScreenSpot-v2.	★★★★★		G UI-Venus 72B	95.3%
494	SEAL-0 O	Agentic web search	Evaluation of multi-step browsing agents on search, evidence gathering, and synthesis tasks.	★★★★★		🇨🇳 Kimi-K2.5 Thinking	57.4%
495	SEED-Bench-2-Plus O	Multimodal evaluation	SEED-Bench-2-Plus overall accuracy.	★★★★★		🇺🇸 Claude 3.7 Sonnet	72.9%
496	SEED-Bench-Img O	Multimodal image understanding	SEED-Bench image-only subset (SEED-Bench-Img).	★★★★★		G Bagel 14B	78.5%
497	SEED-Bench o	Multimodal evaluation	SEED-Bench comprehensive multimodal understanding benchmark evaluating generative comprehension across multiple dimensions.	★★★★★		🇺🇸 LFM2-VL-3B	76.5%
498	SFE o	Multimodal reasoning	Structured factual evaluation for multimodal models.	★★★★★		🇺🇸 Gemini 3 Pro	61.9%
499	Showdown O	GUI agents	Success rate on the Showdown UI interaction benchmark.	★★★★★		🇺🇸 Holo1.5-72B	76.8%
500	SIFO o	Instruction following	Single-turn instruction following benchmark.	★★★★★		🇨🇳 Qwen3-VL-30B-A3B Thinking	66.9%
501	SIFO Multiturn o	Instruction following	Multi-turn SIFO benchmark for sustained instruction adherence.	★★★★★		🇨🇳 Qwen3-VL-30B-A3B Thinking	60.3%
502	SimpleQA O	QA	Simple question answering benchmark.	★★★★★		🇨🇳 DeepSeek V3.2-Exp	97.1%
503	SimpleQA Verified o	QA	Verified SimpleQA variant for parametric knowledge accuracy.	★★★★★		🇺🇸 Gemini 3 Pro	72.1%
504	SimpleVQA O	General VQA	Lightweight visual question answering set with everyday scenes.	★★★★★		🇨🇳 Kimi-K2.5 Thinking	71.2%
505	SimpleVQA-DS o	General VQA	SimpleVQA variant curated by DeepSeek with everyday image question answering tasks.	★★★★★		🇨🇳 Seed1.5-VL-Thinking	61.3%
506	Social Interaction QA (SIQA) o	Social commonsense QA	Social Interaction QA benchmark evaluating social commonsense and situational reasoning.	★★★★★		🇺🇸 Gemma 3 27B	54.9%
507	SocialIQA o	Social commonsense	Social interaction commonsense QA.	★★★★★		🇺🇸 Gemma 3 PT 27B	54.9%
508	SpatialViz O	Mental visualization	Mental visualization benchmark.	★★★★★		🇺🇸 GPT-5.2	65.8%
509	Spider O	Text-to-SQL	Complex text-to-SQL benchmark over cross-domain databases.	★★★★★		G LLaDA2.0 Flash	82.5%
510	Spiral-Bench O	Safety / sycophancy	A LLM-judged benchmark measuring sycophancy and delusion reinforcement.	★★★★★		🇺🇸 GPT-5	87.0%
511	SQuAD v1.1 o	Reading comprehension	Extractive QA from Wikipedia articles.	★★★★★	566	🇺🇸 Llama 3.1 405B Base	89.3%
512	SQuAD v2.0 o	Reading comprehension	Like v1.1 with unanswerable questions.	★★★★★	566	G LLaDA2.0 Flash	90.0%
513	StreamingBench o	Streaming video	Streaming video understanding benchmark.	★★★★★		G Seed1.8	84.4%
514	SUNRGBD O	3D scene understanding	SUN RGB-D benchmark for indoor scene understanding from RGB-D imagery.	★★★★★		🇺🇸 GPT-5 Mini Minimal	45.8%
515	SuperGPQA O	Graduate-level QA	Harder GPQA variant assessing advanced graduate-level reasoning.	★★★★★		🇺🇸 Gemini 3 Pro	75.3%
516	SWE-Bench O	Code repair	Supervised software engineering benchmark across many repos and issues.	★★★★★	3442	🇺🇸 GPT-5 Codex	74.5%
517	SWE-Bench Multilingual O	Code repair (multilingual)	Multilingual variant of SWE-Bench for issue fixing.	★★★★★		🇺🇸 Claude Opus 4.5 Thinking	77.5%
518	SWE-Bench (OpenHands) o	Code repair	SWE-Bench results using the OpenHands autonomous coding agent.	★★★★★	3442	🇺🇸 NVIDIA-Nemotron-3-Nano-30B-A3B-BF16	38.8%
519	SWE-Bench Pro o	Software engineering	Full SWE-Bench Pro benchmark for software-engineering agents.	★★★★★		🇺🇸 GPT-5.2 Thinking	55.6%
520	SWE-Bench Pro (Public) o	Software engineering	Public subset of the SWE-Bench Pro benchmark for software-engineering agents.	★★★★★		🇺🇸 GPT-5	23.3%
521	SWE-Bench Verified O	Code repair	Verified subset of SWE-Bench for issue fixing.	★★★★★		🇺🇸 Claude Opus 4.5	80.9%
522	SWE-Dev o	Code repair	Software engineering development and bug fixing benchmark.	★★★★★		🇺🇸 Claude Sonnet 4	67.1%
523	SWE-Lancer o	Code repair (freelance tasks)	Software engineering benchmark using real freelance-style issues.	★★★★★		🇺🇸 GPT-5.1 Codex-Max	79.9%
524	SWE-Lancer Diamond o	Code repair (freelance)	Diamond subset of SWE-Lancer focusing on the hardest freelance-style issues.	★★★★★		🇺🇸 GPT-4.5	32.6%
525	SWE-Perf o	Code repair	Software engineering benchmark focused on performance-oriented fixes.	★★★★★		🇺🇸 Gemini 3 Pro	6.5%
526	SWE-Review o	Code review	Software engineering review benchmark for assessing code review quality.	★★★★★		🇺🇸 Claude Opus 4.5	16.2%
527	SWT-Bench o	Code repair	Software tool-use benchmark for code tasks.	★★★★★		🇺🇸 GPT-5.2 Thinking	80.7%
528	SysBench o	System prompts	System prompt understanding and adherence benchmark.	★★★★★		🇺🇸 GPT-4.1	74.1%
529	TAU1-Airline O	Agent tasks (airline)	Tool-augmented agent evaluation in airline scenarios (TAU1).	★★★★★		G openPangu-R-72B-2512 Slow Thinking	56.0%
530	TAU1-Retail O	Agent tasks (retail)	Tool-augmented agent evaluation in retail scenarios (TAU1).	★★★★★		G openPangu-R-72B-2512 Slow Thinking	73.0%
531	TAU2-Airline O	Agent tasks (airline)	Tool-augmented agent evaluation in airline scenarios (TAU2).	★★★★★		🇨🇳 LongCat-Flash-Thinking-2601	76.5%
532	TAU2-Retail O	Agent tasks (retail)	Tool-augmented agent evaluation in retail scenarios (TAU2).	★★★★★		🇺🇸 Claude Opus 4.5	88.9%
533	TAU2-Telecom O	Agent tasks (telecom)	Tool-augmented agent evaluation in telecom scenarios (TAU2).	★★★★★		🇨🇳 LongCat-Flash-Thinking-2601	99.3%
534	TempCompass o	Temporal reasoning	Temporal reasoning benchmark evaluating understanding of time-related concepts in videos and images.	★★★★★		🇺🇸 Gemini 3 Pro	88.0%
535	Terminal-Bench O	Agent terminal tasks	Command-line task completion benchmark for agents.	★★★★★	637	🇺🇸 Claude Sonnet 4.5 (Thinking)	61.3%
536	Terminal-Bench 2.0 O	Agent terminal tasks	Second-generation Terminal-Bench leaderboard for end-to-end terminal agents.	★★★★★		G IQuest-Coder-V1-40B-Loop-Instruct	81.4%
537	Terminal-Bench Hard O	Agent terminal tasks	Hard subset of Terminal-Bench command-line agent tasks.	★★★★★		🇺🇸 GPT-5.1 High	43.0%
538	Terminal-Bench Terminus o	Agent terminal tasks	Terminal-Bench Terminus track assessing end-to-end terminal tool use.	★★★★★		🇺🇸 GPT-4.1	30.3%
539	TextQuests O	Text-based video games	Text-based video game benchmark.	★★★★★		🇺🇸 Gemini 3 Pro	41.0%
540	TextQuests Harm O	Harmful propensities	Harmfulness evaluation on TextQuests scenarios.	★★★★★		🇺🇸 Grok 4.1 Fast	↓ 9.1%
541	TextVQA O	Text-based VQA	Visual question answering that requires reading text in images.	★★★★★		G PLM-8B	86.5%
542	TIIF-Bench Long O	Text-to-image	TIIF-Bench long prompt score for text-to-image generation.	★★★★★		G Seedream 4.5	88.5%
543	TIIF-Bench Short O	Text-to-image	TIIF-Bench short prompt score for text-to-image generation.	★★★★★		G Nano Banana 2.0	91.0%
544	TLDR9+ o	Summarization	Long-form summarization benchmark with nine-domain TLDR prompts plus extended variations.	★★★★★		G MobileLLM P1	16.8%
545	TOMATO o	Temporal understanding	Temporal ordering and motion analysis benchmark (TOMATO).	★★★★★		G Seed1.8	60.8%
546	Tool-Decathlon o	Agent tool-use	Composite tool-use suite measuring multi-domain tool invocation success (Pass@1).	★★★★★		🇺🇸 Claude Sonnet 4.5	38.6%
547	Toolathlon O	Agentic software tasks	Long-horizon, real-world software tool-use tasks.	★★★★★		🇺🇸 Gemini 3 Flash	49.4%
548	TreeBench o	Reasoning with tree structures	Evaluates hierarchical/tree-structured reasoning and planning capabilities in LLMs/VLMs.	★★★★★		🇨🇳 GLM-4.6V	51.4%
549	TriQA o	Knowledge QA	Triadic question answering benchmark evaluating world knowledge and reasoning.	★★★★★		🇫🇷 Mixtral 8x22B	82.2%
550	TriviaQA O	Open-domain QA	Open-domain question answering benchmark built from trivia and web evidence.	★★★★★		🇺🇸 Gemma 3 PT 27B	85.5%
551	TriviaQA-Wiki o	Open-domain QA	TriviaQA subset answering using Wikipedia evidence.	★★★★★		🇺🇸 Llama 3.1 405B Base	91.8%
552	TrustLLM o	Safety / reliability	TrustLLM benchmark for trustworthiness and safety behaviors.	★★★★★		🇨🇳 Qwen3-Coder-480B-A35B-Instruct	88.4%
553	TruthfulQA O	Truthfulness / hallucination	Measures whether a model imitates human falsehoods (truthfulness).	★★★★★		G SOLAR-10.7B-Instruct-v1.0	71.4%
554	TruthfulQA (DE) o	Truthfulness / hallucination (German)	German translation of the TruthfulQA benchmark.	★★★★★		🇺🇸 Llama 3.3 70B Instruct	0.2%
555	TVBench o	TV comprehension	Benchmark for TV show video comprehension and QA.	★★★★★		G Seed1.8	71.5%
556	TydiQA o	Cross-lingual QA	Typologically diverse QA across languages.	★★★★★	313	🇺🇸 Llama 3.1 405B Base	34.3%
557	U-Artifacts o	Agentic coding artifacts	Benchmark focusing on generated code artifacts quality.	★★★★★		🇺🇸 Gemini 3 Pro	57.8%
558	V* O	Multimodal reasoning	V* benchmark accuracy.	★★★★★		🇨🇳 Qwen3-VL-8B-Instruct	86.4%
559	VCRBench o	Visual commonsense reasoning	Visual commonsense reasoning benchmark.	★★★★★		G Seed1.8	59.8%
560	VCT O	Virology capability (protocol troubleshooting)	Virology Capabilities Test: a benchmark that measures an LLM's ability to troubleshoot complex virology laboratory protocols.	★★★★★		🇺🇸 Gemini 2.5 Pro	100.0%
561	Vending-Bench 2 O	Long-horizon agentic tasks	Long-horizon agentic task benchmark evaluating sustained goal completion.	★★★★★		🇺🇸 Gemini 3 Pro	5478.2%
562	Vibe Android o	Vibe evaluation (Android)	Vibe evaluation on Android tasks.	★★★★★		🇺🇸 Claude Opus 4.5	92.2%
563	Vibe Average o	Vibe evaluation	Aggregate Vibe evaluation score.	★★★★★		G MiniMax M2.1	88.6%
564	Vibe Backend o	Vibe evaluation (backend)	Vibe evaluation on backend tasks.	★★★★★		🇺🇸 Claude Opus 4.5	98.0%
565	Vibe iOS o	Vibe evaluation (iOS)	Vibe evaluation on iOS tasks.	★★★★★		🇺🇸 Claude Opus 4.5	90.0%
566	Vibe Simulation o	Vibe evaluation (simulation)	Vibe evaluation on simulation tasks.	★★★★★		🇺🇸 Gemini 3 Pro	89.2%
567	Vibe Web o	Vibe evaluation (web)	Vibe evaluation on web tasks.	★★★★★		G MiniMax M2.1	91.5%
568	VibeEval O	Aesthetic/visual quality	VLM aesthetic evaluation with GPT scores.	★★★★★		🇺🇸 Gemini 2.5 Pro	76.4%
569	Video-MME O	Video understanding (multimodal)	Multimodal evaluation of video understanding and reasoning.	★★★★★		🇨🇳 Qwen3-VL 32B Instruct	76.6%
570	VideoHolmes o	Video QA	Video question answering benchmark focused on detective-style clues.	★★★★★		G Seed1.8	65.5%
571	VideoMME o	Multimodal video evaluation	Video multimodal evaluation suite (VideoMME).	★★★★★		🇺🇸 Gemini 3 Pro	88.4%
572	VideoMME (w/o sub) O	Video understanding	Video understanding benchmark without subtitles.	★★★★★		🇺🇸 Gemini 2.5 Pro	85.1%
573	VideoMME (w/sub) o	Video understanding	Video understanding benchmark with subtitles.	★★★★★		🇨🇳 GLM-4.5V	80.7%
574	VideoMMMU O	Multimodal video understanding	Video-based extension of MMMU evaluating temporal multimodal reasoning and perception across disciplines.	★★★★★		🇺🇸 Gemini 3 Pro	87.6%
575	VideoReasonBench o	Video reasoning	Video reasoning benchmark assessing temporal and causal understanding.	★★★★★		🇺🇸 Gemini 2.5 Pro	59.7%
576	VideoSimpleQA o	Video QA	Simple question answering over short videos.	★★★★★		🇺🇸 Gemini 3 Pro	71.9%
577	ViSpeak o	Video dialogue	Video-grounded dialogue and description benchmark.	★★★★★		🇺🇸 Gemini 3 Pro	89.0%
578	VisualPuzzle o	Visual reasoning	Visual puzzle solving benchmark evaluating reasoning and pattern recognition capabilities.	★★★★★		🇺🇸 GPT-5 High	57.8%
579	VisualWebBench O	Web UI understanding	Average accuracy on VisualWebBench.	★★★★★		🇺🇸 Holo1.5-72B	83.8%
580	VisuLogic O	Visual logical reasoning	Logical reasoning and compositionality benchmark for visual-language models.	★★★★★		🇨🇳 ERNIE-4.5-VL-28B-A3B-Thinking	52.5%
581	VitaBench O	Industry QA	Industry-focused benchmark evaluating domain QA performance.	★★★★★		🇺🇸 Claude Opus 4.5	56.3%
582	VL-RewardBench o	Reward modeling (VL)	Reward alignment benchmark for VLMs.	★★★★★		🇺🇸 Claude 3.7 Sonnet	67.4%
583	VLMs are Biased o	Multimodal bias	Evaluates whether VLMs truly 'see' vs. relying on memorized knowledge; measures bias toward non-visual priors.	★★★★★	90	🇺🇸 o4 mini	20.2%
584	VLMs are Blind O	Visual grounding robustness	Evaluates failure modes of VLMs in grounding and perception tasks.	★★★★★		G MiMo-VL 7B-RL	79.4%
585	VLMsAreBiased o	Multimodal bias	Benchmark evaluating biases in vision-language models.	★★★★★		G Seed1.8	62.0%
586	VLMsAreBlind o	Multimodal robustness	Benchmark probing robustness of vision-language models to visual perturbations.	★★★★★		🇺🇸 Gemini 3 Pro	97.5%
587	VoiceBench AdvBench O	VoiceBench	VoiceBench adversarial safety evaluation.	★★★★★		🇨🇳 Qwen3-Omni-30B-A3B-Thinking	99.4%
588	VoiceBench AlpacaEval o	VoiceBench	VoiceBench evaluation on AlpacaEval instructions.	★★★★★		🇨🇳 Qwen3-Omni-Flash-Thinking	96.8%
589	VoiceBench BBH o	VoiceBench	VoiceBench evaluation on Big-Bench Hard prompts.	★★★★★		🇺🇸 Gemini 2.5 Pro	92.6%
590	VoiceBench CommonEval O	VoiceBench	VoiceBench evaluation on CommonEval.	★★★★★		🇨🇳 Qwen3-Omni-Flash-Instruct	91.0%
591	VoiceBench IFEval o	VoiceBench	VoiceBench instruction-following evaluation (IFEval).	★★★★★		🇺🇸 Gemini 2.5 Pro	85.7%
592	MMAU v05.15.25 o	Audio reasoning	Audio reasoning benchmark MMAU v05.15.25.	★★★★★		🇨🇳 Qwen3-Omni-Flash-Instruct	77.6%
593	VoiceBench MMSU O	VoiceBench	VoiceBench MMSU benchmark (voice modality).	★★★★★		🇨🇳 Qwen3-Omni-Flash-Thinking	84.3%
594	VoiceBench MMSU (Audio) o	Audio reasoning	Audio reasoning MMSU results.	★★★★★		🇺🇸 Gemini 2.5 Pro	77.7%
595	VoiceBench OpenBookQA o	VoiceBench	VoiceBench results on OpenBookQA prompts.	★★★★★		🇨🇳 Qwen3-Omni-Flash-Thinking	95.0%
596	VoiceBench SD-QA O	VoiceBench	VoiceBench Spoken Dialogue QA results.	★★★★★		🇺🇸 Gemini 2.5 Pro	90.1%
597	VoiceBench WildVoice O	VoiceBench	VoiceBench evaluation on WildVoice dataset.	★★★★★		🇺🇸 Gemini 2.5 Pro	93.4%
598	VPCT o	Multimodal reasoning	Visual perception and comprehension test.	★★★★★		🇺🇸 Gemini 3 Pro	90.0%
599	VQAv2 O	Visual question answering	Standard Visual Question Answering v2 benchmark on natural images.	★★★★★		🇺🇸 Molmo2-8B	87.0%
600	VSI-Bench O	Spatial intelligence	Visual spatial intelligence benchmark covering 3D reasoning and spatial inference tasks.	★★★★★		🇨🇳 Qwen3-VL-30B-A3B Instruct	63.2%
601	WebClick O	GUI agents	Task success on the WebClick UI agent benchmark.	★★★★★		🇺🇸 Claude Sonnet 4	93.0%
602	WebDev Arena O	Web development agents	Arena evaluation for autonomous web development agents.	★★★★★		🇺🇸 GPT-5	1483
603	WebQuest-MultiQA o	Web agents	Multi-question web search and interaction tasks.	★★★★★		🇨🇳 GLM-4.5V	60.6%
604	WebQuest-SingleQA o	Web agents	Single-question web search and interaction tasks.	★★★★★		🇨🇳 GLM-4.6V	79.5%
605	WebSrc O	Web QA	Webpage question answering (SQuAD F1).	★★★★★		🇺🇸 Holo1.5-72B	97.2%
606	WebVoyager o	Web agents	Web navigation and interaction tasks for LLM agents.	★★★★★		🇨🇳 GLM-4.6V	81.0%
607	WebVoyager2 o	Web agents	Web navigation and interaction tasks for LLM agents (v2).	★★★★★		🇨🇳 GLM-4.5V	84.4%
608	WebWalkerQA o	Web agents	WebWalker tasks evaluating autonomous browsing question answering performance.	★★★★★		🇨🇳 Tongyi DeepResearch	72.2%
609	WeMath o	Math reasoning	Math reasoning benchmark spanning diverse curricula and difficulty levels.	★★★★★		🇨🇳 GLM-4.6V	69.8%
610	WideSearch o	Web search	Wide web search and QA benchmark.	★★★★★		🇺🇸 Claude Opus 4.5 Thinking	76.2%
611	Wild-Jailbreak o	Safety / jailbreak	Adversarial jailbreak benchmark evaluating refusal robustness.	★★★★★		🇺🇸 GPT-OSS 120B (High)	98.2%
612	WildBench V2 o	Instruction following	WildBench V2 human preference benchmark for instruction following and helpfulness.	★★★★★		🇫🇷 Mistral Small 3.2 24B Instruct	65.3%
613	WildGuardTest o	Safety	WildGuardTest safety benchmark.	★★★★★		G IQuest-Coder-V1-40B-Thinking	86.8%
614	Winogender o	Gender bias (coreference)	Coreference resolution dataset for measuring gender bias.	★★★★★		🇺🇸 Llama 3.3 70B Instruct	84.3%
615	WinoGrande O	Coreference reasoning	Large-scale adversarial Winograd Schema-style pronoun resolution.	★★★★★	99	🇺🇸 OLMo-3-Think-32B	90.3%
616	WinoGrande (DE) o	Coreference reasoning (German)	German translation of the WinoGrande pronoun resolution benchmark.	★★★★★		🇺🇸 Llama-3_1-70B-TFree-HAT-SFT	0.8%
617	WMDP Bio o	Biosecurity knowledge	Weapons of Mass Destruction Proxy benchmark for biosecurity, measuring hazardous biological knowledge without info hazards.	★★★★★		🇺🇸 Zephyr 7B	↓ 63.7%
618	WMDP Chem o	Chemical security knowledge	WMDP benchmark for chemical security, evaluating knowledge relevant to chemical weapons development.	★★★★★		🇺🇸 Zephyr 7B	↓ 45.8%
619	WMDP Cyber o	Cybersecurity knowledge	WMDP benchmark for cybersecurity, assessing knowledge that could aid in cyber weapons development.	★★★★★		🇺🇸 Zephyr 7B	↓ 44.0%
620	WMT16 En–De o	Machine translation	WMT16 English–German translation benchmark (news).	★★★★★		🇺🇸 Llama 3.3 70B Instruct	38.8%
621	WMT16 En–De (Instruct) o	Machine translation	Instruction-tuned evaluation on the WMT16 English–German translation set.	★★★★★		🇺🇸 Llama 3.3 70B Instruct	37.9%
622	WMT24++ O	Machine translation	Extended WMT 2024 evaluation across multiple language pairs.	★★★★★		🇨🇳 Qwen3-235B-A22B-Thinking-2507	94.7%
623	WorldTravel2 (multi-modal) o	Travel planning (multimodal)	WorldTravel2 benchmark multimodal track.	★★★★★		🇺🇸 Gemini 3 Pro	47.2%
624	WorldTravel2 (text) o	Travel planning (text)	WorldTravel2 benchmark text-only track.	★★★★★		🇺🇸 GPT-5 High	56.4%
625	WorldVQA o	World knowledge VQA	Visual question answering requiring world knowledge and commonsense reasoning.	★★★★★		🇺🇸 Gemini 3 Pro	47.4%
626	WritingBench O	Writing quality	General-purpose writing quality benchmark.	★★★★★		🇨🇳 Qwen3-235B-A22B-Thinking-2507	88.3%
627	WSC O	Coreference reasoning	Classic Winograd Schema Challenge measuring commonsense coreference.	★★★★★		🇺🇸 Gemma 3 PT 27B	91.9%
628	xBench-DeepSearch O	Agentic research	Evaluates multi-hop deep research workflows on xBench DeepSearch tasks.	★★★★★		🇺🇸 GPT-5 High	77.9%
629	XpertBench (Edu) o	Economics/education	XpertBench education domain subset.	★★★★★		🇺🇸 GPT-5 High	56.9%
630	XpertBench (Fin) o	Economics/finance	XpertBench finance domain subset.	★★★★★		🇺🇸 GPT-5 High	64.5%
631	XpertBench (Humanities) o	Economics/humanities	XpertBench humanities domain subset.	★★★★★		🇺🇸 GPT-5 High	68.5%
632	XpertBench (Law) o	Economics/legal	XpertBench legal domain subset.	★★★★★		🇺🇸 Claude Sonnet 4.5	58.7%
633	XpertBench (Research) o	Economics/research	XpertBench research domain subset.	★★★★★		🇺🇸 GPT-5 High	48.2%
634	XSTest o	Safety	XSTest safety benchmark.	★★★★★		G IQuest-Coder-V1-40B-Thinking	94.3%
635	ZebraLogic O	Logical reasoning	Logical reasoning benchmark assessing complex pattern and rule inference.	★★★★★		🇨🇳 Qwen3-VL 32B Thinking	96.1%
636	ZeroBench O	Zero-shot generalization	Evaluates zero-shot performance across diverse tasks without task-specific finetuning.	★★★★★		🇨🇳 GLM-4.5V	23.4%
637	ZeroBench (sub) O	Zero-shot generalization	Subset of ZeroBench targeting harder zero-shot reasoning cases.	★★★★★		🇺🇸 Gemini 2.5 Pro	33.8%
638	ZeroSCROLLS BookSumSort o	Long-context summarization	ZeroSCROLLS split based on BookSumSort long-form summarization.	★★★★★		🇺🇸 GPT-4	60.5%
639	ZeroSCROLLS GovReport o	Long-context summarization	ZeroSCROLLS split based on the GovReport summarization benchmark.	★★★★★		G CoLT5	41.0%
640	ZeroSCROLLS MuSiQue o	Long-context reasoning	ZeroSCROLLS split derived from MuSiQue multi-hop QA.	★★★★★		🇺🇸 Llama 3.3 70B Instruct	52.2%
641	ZeroSCROLLS NarrativeQA o	Long-context QA	ZeroSCROLLS split based on the NarrativeQA reading comprehension benchmark.	★★★★★		🇺🇸 Claude v1.3	32.6%
642	ZeroSCROLLS Qasper o	Long-context QA	ZeroSCROLLS split based on the Qasper paper QA benchmark.	★★★★★		G FLAN-UL2	56.9%
643	ZeroSCROLLS QMSum o	Long-context summarization	ZeroSCROLLS split based on the QMSum meeting summarization benchmark.	★★★★★		G CoLT5	22.5%
644	ZeroSCROLLS QuALITY o	Long-context QA	ZeroSCROLLS split based on the QuALITY reading comprehension benchmark.	★★★★★		🇺🇸 GPT-4	89.2%
645	ZeroSCROLLS SpaceDigest o	Long-context summarization	ZeroSCROLLS SpaceDigest extractive summarization task.	★★★★★		🇺🇸 Llama-3_1-70B-TFree-HAT-SFT	77.9%
646	ZeroSCROLLS SQuALITY o	Long-context summarization	ZeroSCROLLS split based on the SQuALITY long-form summarization benchmark.	★★★★★		🇺🇸 GPT-4	22.6%
647	ZeroSCROLLS SummScreenFD o	Long-context summarization	ZeroSCROLLS split based on the SummScreenFD summarization benchmark.	★★★★★		G CoLT5	20.0%

Model Size

Log scale

Open source Commercial

Release Date

Open source Commercial