Benchmark Catalog
34478 public benchmarks carry scores in the current fit, with source links and saturation forecasts. The catalogue on this page tracks more boards than the fit uses. The most broadly covered benchmarks are listed below.
| Benchmark | Category | Metric | Models | Saturation forecast |
|---|---|---|---|---|
| Open Portuguese LLM - ASSIN2 RTE | Macro F1 (%) | 638 | Estimated already saturated. | |
| Open Portuguese LLM - BLUEX | Accuracy (%) | 638 | Estimated already saturated. | |
| Open Portuguese LLM - ENEM | Accuracy (%) | 638 | Estimated already saturated. | |
| Open Portuguese LLM - FaQuAD NLI | Macro F1 (%) | 638 | Estimated already saturated. | |
| Open Portuguese LLM - OAB Exams | Accuracy (%) | 638 | Around February 2027. | |
| Open LLM Leaderboard - BBH | Score | 604 | Estimated already saturated. | |
| Open LLM Leaderboard - GPQA | Score | 604 | Estimated already saturated. | |
| Open LLM Leaderboard - IFEval | Score | 604 | Estimated already saturated. | |
| Open LLM Leaderboard - MATH Level 5 | Score | 604 | Estimated already saturated. | |
| Open LLM Leaderboard - MMLU-Pro | Score | 604 | Estimated already saturated. | |
| Open LLM Leaderboard - MuSR | Score | 604 | Estimated already saturated. | |
| AA Humanity's Last Exam | General Knowledge & Language | Accuracy (%) | 546 | Around April 2027. |
| AA CritPt | Math, Logic & Reasoning | Accuracy (%) | 498 | Around May 2027. |
| AA GPQA Diamond | Math, Logic & Reasoning | Accuracy (%) | 495 | Estimated already saturated. |
| AA Long Context Reasoning | General Knowledge & Language | Accuracy (%) | 484 | Around February 2027. |
| AA Omniscience | General Knowledge & Language | Score | 479 | Around December 2027. |
| AA-Omniscience Accuracy | Accuracy (%) | 479 | Around December 2027. | |
| AA-Omniscience Hallucination Rate | Hallucination Rate (%) | 479 | Not forecast. | |
| Wolfram LLM Benchmarking Project | Coding & Software Engineering | Correct Functionality (%) | 381 | Around February 2027. |
| AA IFBench | General Knowledge & Language | Accuracy (%) | 361 | Around February 2027. |
| AA TAU-2 Bench | Agentic & Tool Use | Accuracy (%) | 351 | Estimated already saturated. |
| AA Terminal-Bench Hard | Coding & Software Engineering | Accuracy (%) | 345 | Around February 2027. |
| LLM Stats Score | LLM Stats Score (conservative rating) | 342 | Around December 2027. | |
| Tau2-Bench Telecom | Agentic & Tool Use | Success Rate (%) | 340 | Estimated already saturated. |
| Open LLM Leaderboard v1 - ARC Challenge | Normalized accuracy (%) (25-shot) | 333 | Estimated already saturated. | |
| Open LLM Leaderboard v1 - GSM8K | Accuracy (%) (5-shot) | 333 | Estimated already saturated. | |
| Open LLM Leaderboard v1 - HellaSwag | Normalized accuracy (%) (10-shot) | 333 | Estimated already saturated. | |
| Open LLM Leaderboard v1 - MMLU | Accuracy (%) (5-shot) | 333 | Estimated already saturated. | |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | MC2 (%) (0-shot) | 333 | Estimated already saturated. | |
| Open LLM Leaderboard v1 - WinoGrande | Accuracy (%) (5-shot) | 333 | Estimated already saturated. | |
| Tinybird AI SQL Benchmark - First-Attempt Success Rate | Questions answered with a valid query on the first attempt (%) | 329 | Estimated already saturated. | |
| Tinybird AI SQL Benchmark - Success Rate | Questions answered with a valid query within 3 retries (%) | 329 | Estimated already saturated. | |
| Chatbot Arena (Text - English) | Arena Score | 328 | Forecast unavailable. | |
| Chatbot Arena (Text - Hard Prompts) | Arena Score | 328 | Forecast unavailable. | |
| Chatbot Arena (Text - Instruction Following) | Arena Score | 328 | Forecast unavailable. | |
| Chatbot Arena (Text - Non-English) | Arena Score | 328 | Forecast unavailable. | |
| Chatbot Arena (Text - Software & IT Services) | Arena Score | 328 | Forecast unavailable. | |
| Chatbot Arena (Text) | Elo | 328 | Around November 2027. | |
| Chatbot Arena (Text - Creative Writing) | Arena Score | 327 | Forecast unavailable. | |
| Chatbot Arena (Text - Entertainment, Sports & Media) | Arena Score | 327 | Forecast unavailable. | |
| Chatbot Arena (Text - Hard Prompts (English)) | Arena Score | 327 | Forecast unavailable. | |
| Chatbot Arena (Text - Life, Physical & Social Science) | Arena Score | 327 | Forecast unavailable. | |
| Chatbot Arena (Text - Multi-Turn) | Arena Score | 327 | Forecast unavailable. | |
| Chatbot Arena (Text - Writing, Literature & Language) | Arena Score | 327 | Forecast unavailable. | |
| Chatbot Arena (Text - Coding) | Arena Score | 326 | Forecast unavailable. | |
| AI Chess Leaderboard (Reasoning) | Games & Puzzles | Elo | 325 | Around January 2028. |
| Chatbot Arena (Text - Business, Management & Financial Ops) | Arena Score | 324 | Forecast unavailable. | |
| Tinybird AI SQL Benchmark - Exactness | Result exactness vs human reference queries (0-100) | 323 | Around July 2028. | |
| SpeechMap Compliance | % Requests Completed | 321 | Forecast unavailable. | |
| ObviousBench | Answer pass³ (%) | 321 | Estimated already saturated. | |
| Chatbot Arena (Text - Math) | Arena Score | 320 | Forecast unavailable. | |
| Chatbot Arena (Text - Longer Query) | Arena Score | 317 | Forecast unavailable. | |
| Chatbot Arena (Text - Mathematical) | Arena Score | 317 | Forecast unavailable. | |
| Chatbot Arena (Text - Chinese) | Arena Score | 312 | Forecast unavailable. | |
| Chatbot Arena (Text - Legal & Government) | Arena Score | 312 | Forecast unavailable. | |
| Chatbot Arena (Text - Medicine & Healthcare) | Arena Score | 312 | Forecast unavailable. | |
| Chatbot Arena (Text - Russian) | Arena Score | 310 | Forecast unavailable. | |
| Open Korean LLM - Ko-EQ-Bench | EQ-Bench score | 308 | Estimated already saturated. | |
| Open Korean LLM - Ko-GPQA-Diamond | Normalized accuracy (%) | 308 | Estimated already saturated. | |
| Open Korean LLM - Ko-GSM8K (flexible extract) | Exact match, flexible extract (%) | 308 | Estimated already saturated. |
Interactive version: theaggregate.ai/benchmarks/catalog · How It Works · Data refreshed daily, snapshot 2026-11-14.