Evaluation registry
Browse published benchmark definitions, capability categories and source-native model result pages.
Data as of 2026-08-07
A quick view of registry breadth and current model coverage.
Open a category to compare its benchmark registry and leading result sets.
| reasoning | 245 | 34 | 104 |
| multimodal | 152 | 0 | 65 |
| math | 84 | 25 | 129 |
| agents | 49 | 0 | 19 |
| safety | 16 | 0 | 11 |
| code | 15 | 0 | 4 |
| general | 15 | 4 | 31 |
| language | 11 | 2 | 23 |
| physics | 7 | 3 | 233 |
| spatial reasoning | 7 | 0 | 26 |
| healthcare | 6 | 0 | 9 |
| productivity | 6 | 0 | 3 |
| summarization | 6 | 0 | 5 |
| structured output | 5 | 1 | 65 |
| image to text | 4 | 0 | 22 |
| long context | 4 | 0 | 52 |
| speech to text | 4 | 0 | 6 |
| uncategorized | 4 | 0 | 12 |
| audio | 2 | 0 | 1 |
| finance | 2 | 0 | 1 |
| image-generation | 2 | 0 | 1 |
| instruction following | 2 | 1 | 28 |
| 3d | 1 | 0 | 1 |
| creativity | 1 | 1 | 13 |
| factuality | 1 | 0 | 1 |
| frontend development | 1 | 0 | 3 |
| legal | 1 | 1 | 15 |
| medical | 1 | 0 | 1 |
| memory | 1 | 0 | 1 |
| psychology | 1 | 0 | 9 |
| question answering | 1 | 0 | 1 |
| research | 1 | 0 | 1 |
| robotics | 1 | 0 | 1 |
| video | 1 | 0 | 1 |
| vision | 1 | 0 | 16 |
Open any benchmark to inspect its leaderboard, scoring direction, evidence fields and programmatic FAQ.
| GPQA | physics | GPQA | Score | 233 | featured | C | Yes |
| MMLU-Pro | math | MMLU-Pro | Score | 129 | featured | B | Yes |
| AIME 2025 | math | AIME 2025 | Score | 114 | featured | C | Yes |
| SWE-Bench Verified | reasoning | SWE-Bench Verified | Score | 104 | featured | C | No |
| MMLU | math | MMLU | Score | 100 | featured | B | Yes |
| Humanity's Last Exam | math | Humanity's Last Exam | Score | 92 | featured | B | No |
| LiveCodeBench | reasoning | LiveCodeBench | Score | 73 | featured | C | Yes |
| MATH | math | MATH | Score | 71 | featured | B | Yes |
| HumanEval | reasoning | HumanEval | Score | 66 | featured | B | Yes |
| IFEval | structured output | IFEval | Score | 65 | featured | B | Yes |
| MMMU-Pro | multimodal | MMMU-Pro | Score | 65 | featured | B | No |
| MMMU | multimodal | MMMU | Score | 63 | featured | B | No |
| BrowseComp | reasoning | BrowseComp | Score | 58 | featured | B | Yes |
| AIME 2024 | math | AIME 2024 | Score | 53 | featured | B | Yes |
| LiveCodeBench v6 | reasoning | LiveCodeBench v6 | Score | 53 | featured | B | Yes |
| nolima | long context | nolima | Score | 52 | featured | C | No |
| MMMLU | math | MMMLU | Score | 49 | featured | B | Yes |
| Terminal-Bench 2.0 | reasoning | Terminal-Bench 2.0 | Score | 49 | featured | C | No |
| GSM8k | math | GSM8k | Score | 48 | featured | B | Yes |
| MMLU-Redux | math | MMLU-Redux | Score | 48 | featured | B | Yes |
| CharXiv-R | multimodal | CharXiv-R | Score | 47 | featured | B | No |
| SimpleQA | reasoning | SimpleQA | Score | 46 | featured | B | Yes |
| SWE-Bench Pro | reasoning | SWE-Bench Pro | Score | 44 | featured | B | No |
| MathVista | math | MathVista | Score | 39 | featured | B | No |
| LiveBench | math | LiveBench | Score | 38 | featured | B | No |
| Tau2 Telecom | reasoning | Tau2 Telecom | Score | 35 | featured | B | No |
| ARC-C | reasoning | ARC-C | Score | 34 | featured | B | Yes |
| SuperGPQA | math | SuperGPQA | Score | 34 | featured | B | Yes |
| SWE-bench Multilingual | reasoning | SWE-bench Multilingual | Score | 34 | featured | B | No |
| HMMT 2025 | math | HMMT 2025 | Score | 33 | featured | B | Yes |
| MBPP | reasoning | MBPP | Score | 33 | featured | B | Yes |
| MATH-500 | math | MATH-500 | Score | 32 | featured | C | Yes |
| MMLU-ProX | math | MMLU-ProX | Score | 32 | featured | B | Yes |
| AI2D | multimodal | AI2D | Score | 32 | featured | B | No |
| MathVision | math | MathVision | Score | 32 | featured | B | No |
| MGSM | math | MGSM | Score | 31 | featured | B | Yes |
| Toolathlon | reasoning | Toolathlon | Score | 31 | featured | B | Yes |
| Include | general | Include | Score | 31 | featured | B | No |
| DROP | math | DROP | Score | 30 | featured | B | Yes |
| MCP Atlas | reasoning | MCP Atlas | Score | 30 | featured | B | Yes |
| Multi-Challenge | reasoning | Multi-Challenge | Score | 29 | featured | C | Yes |
| IFBench | instruction following | IFBench | Score | 28 | featured | B | Yes |
| HellaSwag | reasoning | HellaSwag | Score | 27 | featured | B | Yes |
| Arena Hard | reasoning | Arena Hard | Score | 26 | featured | B | No |
| DocVQA | multimodal | DocVQA | Score | 26 | featured | B | No |
| Finance Agent v2 | reasoning | Finance Agent v2 | Score | 26 | featured | B | No |
| RealWorldQA | spatial reasoning | RealWorldQA | Score | 26 | featured | B | No |
| Tau2 Retail | reasoning | Tau2 Retail | Score | 26 | featured | B | No |
| VideoMMMU | multimodal | VideoMMMU | Score | 26 | featured | B | No |
| HMMT25 | math | HMMT25 | Score | 25 | featured | B | Yes |
| TAU-bench Retail | reasoning | TAU-bench Retail | Score | 25 | featured | B | No |
| Terminal-Bench | reasoning | Terminal-Bench | Score | 25 | featured | B | No |
| ChartQA | multimodal | ChartQA | Score | 24 | featured | B | No |
| LVBench | multimodal | LVBench | Score | 24 | featured | B | No |
| ScreenSpot Pro | multimodal | ScreenSpot Pro | Score | 24 | featured | C | No |
| t2-bench | reasoning | t2-bench | Score | 23 | featured | B | Yes |
| WMT24++ | language | WMT24++ | Score | 23 | featured | B | Yes |
| ERQA | reasoning | ERQA | Score | 23 | featured | C | No |
| MathVista-Mini | math | MathVista-Mini | Score | 23 | featured | B | No |
| PolyMATH | math | PolyMATH | Score | 23 | featured | B | No |
| TAU-bench Airline | reasoning | TAU-bench Airline | Score | 23 | featured | B | No |
| Tau2 Airline | reasoning | Tau2 Airline | Score | 23 | featured | B | No |
| Aider-Polyglot | general | Aider-Polyglot | Score | 22 | featured | B | Yes |
| Winogrande | reasoning | Winogrande | Score | 22 | featured | B | Yes |
| MMStar | multimodal | MMStar | Score | 22 | featured | B | No |
| OCRBench | image to text | OCRBench | Score | 22 | featured | B | No |
| OSWorld-Verified | multimodal | OSWorld-Verified | Score | 22 | featured | B | No |
| BIG-Bench Hard | math | BIG-Bench Hard | Score | 21 | featured | B | Yes |
| MRCR v2 (8-needle) | reasoning | MRCR v2 (8-needle) | Score | 21 | featured | C | Yes |
| Multi-IF | reasoning | Multi-IF | Score | 20 | featured | B | Yes |
| OSWorld | multimodal | OSWorld | Score | 20 | featured | B | No |
| BFCL-v3 | reasoning | BFCL-v3 | Score | 19 | featured | B | Yes |
| IMO-AnswerBench | math | IMO-AnswerBench | Score | 19 | featured | B | Yes |
| DeepSWE 1.1 | agents | DeepSWE 1.1 | Score | 19 | featured | B | No |
| C-Eval | reasoning | C-Eval | Score | 18 | featured | B | Yes |
| SciCode | math | SciCode | Score | 18 | featured | B | Yes |
| TriviaQA | reasoning | TriviaQA | Score | 18 | featured | B | Yes |
| TruthfulQA | reasoning | TruthfulQA | Score | 18 | featured | B | Yes |
| CC-OCR | multimodal | CC-OCR | Score | 18 | featured | B | No |
| MMBench-V1.1 | multimodal | MMBench-V1.1 | Score | 18 | featured | B | No |
| AIME 2026 | math | AIME 2026 | Score | 17 | featured | B | Yes |
| FrontierMath | math | FrontierMath | Score | 17 | featured | B | Yes |
| LongBench v2 | reasoning | LongBench v2 | Score | 17 | featured | C | Yes |
| MM-MT-Bench | multimodal | MM-MT-Bench | Score | 17 | featured | B | No |
| MVBench | multimodal | MVBench | Score | 17 | featured | B | No |
| Terminal-Bench 2.1 | reasoning | Terminal-Bench 2.1 | Score | 17 | featured | B | No |
| Video-MME | multimodal | Video-MME | Score | 17 | featured | B | No |
| CodeForces | math | CodeForces | Score | 16 | featured | B | Yes |
| ARC-AGI v2 | reasoning | ARC-AGI v2 | Score | 16 | featured | B | No |
| Arena-Hard v2 | reasoning | Arena-Hard v2 | Score | 16 | featured | B | No |
| CharXiv-D | multimodal | CharXiv-D | Score | 16 | featured | B | No |
| Hallusion Bench | reasoning | Hallusion Bench | Score | 16 | featured | B | No |
| ODinW | vision | ODinW | Score | 16 | featured | B | No |
| OmniDocBench 1.5 | multimodal | OmniDocBench 1.5 | Score | 16 | featured | B | No |
| ScreenSpot | multimodal | ScreenSpot | Score | 16 | featured | B | No |
| FrontierCode 1.1 | reasoning | FrontierCode 1.1 | Score | 15 | featured | B | Yes |
| WritingBench | legal | WritingBench | Score | 15 | featured | B | Yes |
| AA-LCR | reasoning | AA-LCR | Score | 15 | featured | B | No |
| FrontierSWE | agents | FrontierSWE | Score | 15 | featured | B | No |
| TextVQA | multimodal | TextVQA | Score | 15 | featured | B | No |
| Global-MMLU-Lite | reasoning | Global-MMLU-Lite | Score | 14 | featured | B | Yes |
| LiveBench 20241125 | math | LiveBench 20241125 | Score | 14 | featured | B | No |
| NL2Repo | agents | NL2Repo | Score | 14 | featured | B | No |
| BrowseComp-zh | reasoning | BrowseComp-zh | Score | 13 | featured | B | Yes |
| Creative Writing v3 | creativity | Creative Writing v3 | Score | 13 | featured | B | Yes |
| FACTS Grounding | reasoning | FACTS Grounding | Score | 13 | featured | C | Yes |
| Global PIQA | physics | Global PIQA | Score | 13 | featured | B | Yes |
| HiddenMath | math | HiddenMath | Score | 13 | featured | B | Yes |
| MultiPL-E | language | MultiPL-E | Score | 13 | featured | B | Yes |
| BFCL-V4 | agents | BFCL-V4 | Score | 13 | featured | B | No |
| BLINK | multimodal | BLINK | Score | 13 | featured | B | No |
| Claw-Eval | agents | Claw-Eval | Score | 13 | featured | B | No |
| Legal Agent Benchmark | reasoning | Legal Agent Benchmark | Score | 13 | featured | B | No |
| SimpleVQA | multimodal | SimpleVQA | Score | 13 | featured | B | No |
| BBH | math | BBH | Score | 12 | featured | B | Yes |
| MT-Bench | reasoning | MT-Bench | Score | 12 | featured | B | Yes |
| CharadesSTA | multimodal | CharadesSTA | Score | 12 | featured | B | No |
| InfoVQAtest | multimodal | InfoVQAtest | Score | 12 | featured | B | No |
| MedXpertQA | multimodal | MedXpertQA | Score | 12 | featured | B | No |
| OCRBench-V2 (en) | image to text | OCRBench-V2 (en) | Score | 12 | featured | B | No |
| OptimBench | uncategorized | OptimBench | Score | 12 | featured | C | No |
| BFCL | reasoning | BFCL | Score | 11 | featured | B | Yes |
| BIG-Bench Extra Hard | reasoning | BIG-Bench Extra Hard | Score | 11 | featured | B | Yes |
| Graphwalks BFS <128k | reasoning | Graphwalks BFS <128k | Score | 11 | featured | B | Yes |
| Graphwalks BFS >128k | reasoning | Graphwalks BFS >128k | Score | 11 | featured | B | Yes |
| Graphwalks parents <128k | reasoning | Graphwalks parents <128k | Score | 11 | featured | B | Yes |
| HMMT Feb 26 | math | HMMT Feb 26 | Score | 11 | featured | B | Yes |
| MAXIFE | general | MAXIFE | Score | 11 | featured | B | Yes |
| NOVA-63 | general | NOVA-63 | Score | 11 | featured | B | Yes |
| PIQA | physics | PIQA | Score | 11 | featured | B | Yes |
| CyberGym | safety | CyberGym | Score | 11 | featured | B | No |
| DocVQAtest | multimodal | DocVQAtest | Score | 11 | featured | B | No |
| MMMU (val) | multimodal | MMMU (val) | Score | 11 | featured | B | No |
| MuirBench | multimodal | MuirBench | Score | 11 | featured | B | No |
| OCRBench-V2 (zh) | image to text | OCRBench-V2 (zh) | Score | 11 | featured | B | No |
| AGIEval | math | AGIEval | Score | 10 | featured | B | Yes |
| Aider-Polyglot Edit | general | Aider-Polyglot Edit | Score | 10 | featured | B | Yes |
| BoolQ | reasoning | BoolQ | Score | 10 | featured | B | Yes |
| COLLIE | reasoning | COLLIE | Score | 10 | featured | B | Yes |
| HumanEval+ | reasoning | HumanEval+ | Score | 10 | featured | B | Yes |
| VITA-Bench | reasoning | VITA-Bench | Score | 10 | featured | B | Yes |
| DeepSWE | agents | DeepSWE | Score | 10 | featured | B | No |
| MLVU | multimodal | MLVU | Score | 10 | featured | B | No |
| VideoMME w sub. | multimodal | VideoMME w sub. | Score | 10 | featured | B | No |
| VideoMME w/o sub. | multimodal | VideoMME w/o sub. | Score | 10 | featured | B | No |
Benchmark values stay on their source-native scales. Every registry row uses its unique Benchmark handle for the detail link.