LMArena · GPQA · SWE-bench · HLE · ARC-AGI · OSWorld · BFCL
Benchmarki modeli AI
3086 wyników dla 1079 modeli w 23 publicznych benchmarkach. Każda liczba prowadzi do źródła; dane podane przez producentów są oznaczone.
3086 wyników 1079 modeli 23 benchmarków Zaktualizowano 22 paź 2026
Current champions
The top model on each core benchmark. Only official leaderboards, independent evaluations and compiled data count; vendor self-reports are excluded.
LMArena Text Gemini 4 Argon 1525 Preferencje ludzi GPQA Diamond Gemini 4 Argon 96.4% Nauki ścisłe Humanity's Last Exam GPT-6 Astra 54.8% Wiedza AIME (OTIS Mock AIME 2024–2025) Gemini 4 Argon 100.0% Matematyka SWE-bench Verified Claude Opus 4.7 83.5% Programowanie agentowe Terminal-Bench 2.0 GPT-5.5 84.7% Programowanie agentowe OSWorld (Verified) Claude Sonnet 4.6 72.1% Obsługa komputera τ²-bench Gemini 3.0 Pro 85.3% Narzędzia i agenci BFCL v4 (function calling) Claude Opus 4.5 77.5% Narzędzia i agenci MMLU-Pro Gemini 3.1 Pro 91.2% Wiedza
Macierz model × benchmark
Każda komórka to najlepszy wynik w głównym ustawieniu (pierwszeństwo mają oficjalne rankingi i niezależne testy). ◇ = tylko dane producenta lub z artykułu. Kliknij kolumnę, aby sortować; zaznacz modele, aby porównać.
| Model | LMArena Text | GPQA Diamond | Humanity's Last Exam | AIME (OTIS Mock AIME 2024–2025) | SWE-bench Verified | Terminal-Bench 2.0 | OSWorld (Verified) | τ²-bench | BFCL v4 (function calling) | MMLU-Pro |
|---|---|---|---|---|---|---|---|---|---|---|
| GPT-5.2OpenAI | 1437 | 91.4% | 27.8% | 96.1% | 73.8% | 64.9% | — | 81.6% | 55.9% | 87.4% ◇ |
| Gemini 3 ProGoogle | 1486 | 92.6% | 37.5% | 91.4% | 77.4% | 69.4% | — | 75.9% | 72.5% | 90.1% ◇ |
| Claude Sonnet 4.5Anthropic | 1456 | 82.3% | 13.7% | 77.8% | 74.8% | 46.5% | 62.9% | 72.4% | 73.2% | — |
| GPT-5OpenAI | 1435 | 86.2% | 25.3% | 91.4% | 74.4% | 49.6% | — | 81.6% | — | 87.1% ◇ |
| o3OpenAI | 1432 | 81.8% | 20.3% | 84.4% | 62.3% | — | 23.0% | 73.9% ◇ | 63.0% | — |
| Claude Opus 4.5Anthropic | 1474 | 86.0% | 25.2% | 86.1% | 79.2% | 63.1% | 66.3% ◇ | 79.6% | 77.5% | — |
| Gemini 2.5 Pro (Jun 2025)Google | 1446 | 85.3% | 21.6% | 84.7% | 57.6% | 32.6% | — | — | — | 86.0% ◇ |
| Claude Sonnet 4Anthropic | 1402 | 79.2% | 7.8% | 68.9% | 76.8% | — | 43.9% | 80.5% ◇ | — | — |
| o4-miniOpenAI | 1391 | 79.6% | 18.1% | 81.7% | 64.6% | — | — | 68.3% | 53.2% | — |
| GPT-4.1OpenAI | 1415 | 66.9% | 5.4% | 38.3% | 48.5% | — | — | 74.0% | 54.0% | 81.8% ◇ |
| Claude 3.7 SonnetAnthropic | 1388 | 79.7% | 8.0% | 57.8% | 66.4% | — | 35.8% | 72.1% | — | 84.0% ◇ |
| Qwen2.5-72BAlibaba (Qwen) | 1303 | 49.1% | — | 8.1% | — | — | 5.0% | — | — | 71.6% ◇ |
| Claude Opus 4.7Anthropic | 1501 | 90.2% | 36.2% | 97.8% | 83.5% | 80.2% | — | — | — | — |
| GPT-5.4OpenAI | 1475 | 93.3% | 36.2% | 97.8% | 76.9% | 81.8% | — | — | — | 87.5% ◇ |
| Gemini 3.1 ProGoogle | 1487 | 94.4% | 46.4% | 95.6% | 75.6% | 80.2% | — | — | — | 91.2% |
| Claude Sonnet 4.6Anthropic | 1472 | 87.4% | — | 85.8% | 75.2% | 53.4% | 72.1% | — | — | — |
| Kimi K2.5Moonshot AI | 1450 | 87.6% | 24.4% | 92.2% | 73.8% | 43.2% | 63.3% | — | — | — |
| GPT-5.1OpenAI | 1456 | 87.6% | 23.7% | 88.6% | 68.0% | 47.6% | — | — | — | 86.4% ◇ |
| GPT-5 miniOpenAI | 1390 | 75.0% | 19.4% | 86.7% | 64.7% | 34.8% | — | — | 55.5% | — |
| Claude Opus 4Anthropic | 1426 | 76.3% | 10.7% | 64.4% | 70.7% | — | — | 81.4% ◇ | — | — |
| Gemini 1.5 Pro (Sept 2024)Google | 1351 | 57.2% | 4.6% | 23.1% | — | — | — | — | — | 70.3% |
| Claude 3.5 SonnetAnthropic | 1374 | 54.0% | — | 6.5% | 63.4% | — | — | — | — | 77.6% |
| GPT-4o (May 2024)OpenAI | 1346 | 48.9% | — | 6.3% | 38.8% | — | — | — | — | 72.5% |
| Claude 3 HaikuAnthropic | 1262 | 36.3% | — | 1.8% | 40.6% | — | — | — | — | 42.3% |
| GPT-4 Turbo (Nov 2023)OpenAI | 1325 | 42.4% | — | — | 22.4% | — | — | — | — | 63.7% |
| GLM-5Zhipu AI (Z.ai) | 1458 | 87.8% | — | 80.0% | 72.8% | 52.4% | — | 73.7% | — | 86.0% ◇ |
| Claude Opus 4.6Anthropic | 1504 | 90.5% | 34.4% | 94.4% | 78.7% | 79.8% | — | — | — | — |
| Gemini 3 FlashGoogle | 1473 | 89.4% | — | 95.6% | 75.8% | 64.3% | — | 76.8% | — | — |
| DeepSeek-V3.2DeepSeek | 1425 | 83.4% | — | 87.8% | 70.0% | 39.5% | — | 81.1% ◇ | — | 85.0% ◇ |
| Claude Haiku 4.5Anthropic | 1414 | 71.2% | — | 66.7% | 66.6% | 35.5% | — | — | 68.7% | — |
| GPT-5 nanoOpenAI | 1337 | 69.4% | — | 81.1% | 34.8% | 21.8% | — | — | 51.5% | — |
| Claude Opus 4.1Anthropic | 1450 | 76.8% | 11.5% | 68.9% | 73.3% | 38.0% | — | 82.4% ◇ | — | — |
| GPT-4.1 miniOpenAI | 1383 | 65.8% | — | 44.7% | 23.9% | — | — | 61.4% | 50.5% | — |
| Phi-4Microsoft Research | 1256 | 56.1% | — | 13.8% | — | — | — | — | 28.8% | 70.4% ◇ |
| Llama 3.3 70BMeta | 1318 | 47.4% | — | 5.1% | — | — | — | — | 31.9% | 65.9% |
| Gemini 1.5 Flash (Sep 2024)Google | 1309 | 47.3% | — | 16.3% | — | — | — | — | — | 64.1% |
| Llama 3.1-8BMeta | 1211 | 27.0% | — | 1.7% | — | — | — | — | 25.8% | 36.6% |
| GPT-4o miniOpenAI | 1318 | 37.7% | — | 6.9% | — | — | — | — | — | 63.1% |
| Claude 3 OpusAnthropic | 1322 | 47.2% | — | 4.7% | 15.8% | — | — | — | — | 68.5% |
| Gemini 3.8 FlashGoogle | 1497 | 95.4% | 44.5% | 98.9% | — | — | — | — | — | — |
Wszystkie benchmarki
Programowanie
LMArena WebDevAktywny Arena where two models each build a web app from the same prompt and users vote on the result. 127 modeli · Najlepszy: 1813 LiveCodeBenchDawno nieaktualizowany Coding problems collected continuously from LeetCode, AtCoder and Codeforces with their release dates, so models can be scored only on problems published after their training cut-off. 22 modeli · Najlepszy: 75.8% HumanEval / HumanEval+Nasycony 164 hand-written Python function problems from OpenAI (2021). EvalPlus adds many more tests per problem (HumanEval+) to catch wrong solutions that pass the original tests. 122 modeli · Najlepszy: 89.0%
Ogólne
Open LLM Leaderboard v2Zarchiwizowany Hugging Face's leaderboard of open-weight models, scored on IFEval, BBH, MATH Lvl 5, GPQA, MuSR and MMLU-Pro with normalised scores. The leaderboard was archived in 2025 and no longer accepts submissions. 294 modeli · Najlepszy: 48.0% Artificial Analysis Intelligence IndexTylko link Independent composite index that runs a battery of evaluations plus price and speed measurements across API models. Tylko link
Wiedza
MMLUNasycony About 14,000 multiple-choice questions over 57 subjects, from elementary maths to law and medicine. 158 modeli · Najlepszy: 88.1% MMLU-ProAktywny Harder successor to MMLU: about 12,000 reasoning-heavy questions in 14 disciplines with 10 answer options. 243 modeli · Najlepszy: 91.2% Humanity's Last ExamAktywny About 2,500 expert-written questions across 100+ subjects from the Center for AI Safety and Scale AI, filtered to stump frontier models at creation time. 46 modeli · Najlepszy: 54.8%
Programowanie agentowe
SWE-bench VerifiedSporny 500 human-validated GitHub issues from 12 Python repositories; the system must produce a patch that makes the hidden tests pass. 81 modeli · Najlepszy: 83.5% SWE-bench ProTylko link Scale AI's harder, longer-horizon successor to SWE-bench with a 731-task public split and private/commercial splits. Tylko link Terminal-Bench 2.0Aktywny Hard, realistic tasks an agent must finish in a sandboxed terminal (Stanford × Laude Institute). 45 modeli · Najlepszy: 84.7%
Matematyka
AIME (OTIS Mock AIME 2024–2025)Aktywny AIME-style competition maths (integer answers 0–999). We use Epoch AI's runs on the OTIS Mock AIME 2024–2025 papers, which are less exposed than past official AIME papers. 200 modeli · Najlepszy: 100.0% MATH Level 5Nasycony The hardest (level 5) problems of the MATH competition dataset (Hendrycks et al., 2021). 94 modeli · Najlepszy: 98.1%
Rozumowanie abstrakcyjne
ARC-AGI-1Nasycony Abstract grid puzzles (François Chollet) that test learning a new rule from a few examples. 6 modeli · Najlepszy: 98.5% ARC-AGI-2Aktywny Harder second version of ARC-AGI (2025), designed so that brute-force search is not enough. 4 modeli · Najlepszy: 95.0% ARC-AGI-3Aktywny Interactive, game-like third version of ARC-AGI that tests exploration and learning inside novel environments. 3 modeli · Najlepszy: 99.9%
Obsługa komputera
OSWorld (Verified)Aktywny 369 real computer tasks in a full Ubuntu desktop (browsers, office apps, file manager, terminal) checked by execution-based scripts. 9 modeli · Najlepszy: 72.1% OSWorld 2.0Aktywny Long-horizon successor to OSWorld (2026) with multi-application workflows. 9 modeli · Najlepszy: 31.4%
Narzędzia i agenci
τ²-benchAktywny Sierra's customer-service agent benchmark: the agent follows a policy and uses tools while an LLM-simulated user talks to it (retail, airline, telecom, banking). 43 modeli · Najlepszy: 85.3% BFCL v4 (function calling)Aktywny Berkeley Function Calling Leaderboard: single, parallel and multi-turn tool calls, web search, memory and relevance detection. 80 modeli · Najlepszy: 77.5%
Chiński
CMMLUDawno nieaktualizowany Chinese multitask knowledge benchmark: 67 subjects including China-specific topics. 12 modeli · Najlepszy: 90.3% C-EvalDawno nieaktualizowany Chinese evaluation suite of about 13,900 multiple-choice questions over 52 disciplines and four difficulty levels. 11 modeli · Najlepszy: 68.7% SuperCLUETylko link Periodic Chinese general-capability evaluation of domestic and international models, published as reports. Tylko link
Metoda zbierania
- We read official data files and public datasets (Hugging Face, GitHub, CSV downloads) and never invent or estimate scores.
- Model names from different leaderboards are merged into one model page (for example dated versions and reasoning-effort variants).
- Leaderboards that restrict reuse are cited with their top entries only, or linked without copying.
- Data is refreshed by a repeatable script; each run keeps a dated snapshot so changes can be compared over time.
Typ źródła
- Oficjalny ranking
- The benchmark maintainers' own leaderboard
- Niezależny test
- An independent evaluator ran the model itself (e.g. Epoch AI)
- Podane przez producenta
- Self-reported or submitted by the model developer
- Artykuł / raport
- Reported in a paper or technical report (usually by the developer)
- Zestawienie zewnętrzne
- Compiled by Epoch AI; the original source is not given per row
Źródła danych i licencje
| Źródło | Licencja / warunki | Jak korzystamy | Ostatnio pobrano |
|---|---|---|---|
| LMArena leaderboard dataset LMArena, Arena Leaderboard Dataset (Hugging Face), CC BY 4.0 | CC BY 4.0 | Open licence – full data with attribution | 10 paź 2026 ⚠︎ |
| Epoch AI Benchmarking Hub Epoch AI, 'Capabilities & benchmarking', https://epoch.ai/benchmarks (CC BY 4.0) | CC BY 4.0 | Open licence – full data with attribution | 22 paź 2026 |
| SWE-bench leaderboards (swebench.com) SWE-bench team, swebench.com leaderboards | No explicit licence (NOASSERTION) – factual scores only, with citation | No explicit licence – factual scores only, with citation | 22 paź 2026 |
| LiveCodeBench leaderboard LiveCodeBench (Jain et al.), livecodebench.github.io | No explicit licence on the site repo (benchmark code MIT) – factual scores only, with citation | No explicit licence – factual scores only, with citation | 22 paź 2026 |
| EvalPlus leaderboard EvalPlus team, evalplus.github.io | Apache-2.0 (site repo) | Open licence – full data with attribution | 22 paź 2026 |
| Berkeley Function Calling Leaderboard (BFCL) Gorilla / BFCL team, UC Berkeley | Apache-2.0 (gorilla repo) | Open licence – full data with attribution | 22 paź 2026 |
| τ²-bench leaderboard submissions Sierra Research, τ²-bench | MIT (repo) | Open licence – full data with attribution | 22 paź 2026 |
| MMLU-Pro leaderboard (TIGER-Lab) TIGER-Lab, MMLU-Pro leaderboard | Apache-2.0 (dataset) | Open licence – full data with attribution | 22 paź 2026 |
| Hugging Face Open LLM Leaderboard v2 (archived) Hugging Face, Open LLM Leaderboard (archived 2025) | No licence tag – factual scores only, with citation | No explicit licence – factual scores only, with citation 4576 rows in archive; 353 official-developer models kept | 22 paź 2026 |
| ARC Prize leaderboard ARC Prize Foundation, arcprize.org/leaderboard | ARC Prize Terms: no copying/aggregation for commercial purposes without permission | Restricted – only top entries cited top 10 per set only (terms) | 22 paź 2026 |
| CMMLU leaderboard (GitHub README) Li et al., CMMLU (CC BY-NC-SA 4.0) | CC BY-NC-SA 4.0 | Restricted – only top entries cited | 22 paź 2026 |
| C-Eval (GitHub README, initial release table) Huang et al., C-Eval | Code MIT; dataset CC BY-NC-SA 4.0 | Restricted – only top entries cited | 22 paź 2026 |
| Artificial Analysis Artificial Analysis | Free API requires an API key and attribution; no open bulk data | Not collected – link only | — |
| SuperCLUE CLUE / SuperCLUE | No open data interface | Not collected – link only | — |
| Scale AI SEAL leaderboards (SWE-bench Pro, HLE) Scale AI | No open data interface | Not collected – link only | — |
Dla agentów AI
The same data as JSON: benchmark metadata with licences, every model's best scores and per-benchmark result lists with source links.
/api/benchmarks.json/api/benchmarks/matrix.json/api/benchmarks/<id>.json/llms.txt