LMArena · GPQA · SWE-bench · HLE · ARC-AGI · OSWorld · BFCL
Бенчмарки ШІ-моделей
3086 результатів 1079 моделей на 23 відкритих бенчмарках. Кожне число веде до джерела; дані від розробників позначено окремо.
3086 результатів 1079 моделей 23 бенчмарків Оновлено 22 жовт. 2026 р.
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 Вподобання людей GPQA Diamond Gemini 4 Argon 96.4% Наука Humanity's Last Exam GPT-6 Astra 54.8% Знання AIME (OTIS Mock AIME 2024–2025) Gemini 4 Argon 100.0% Математика SWE-bench Verified Claude Opus 4.7 83.5% Агентне програмування Terminal-Bench 2.0 GPT-5.5 84.7% Агентне програмування OSWorld (Verified) Claude Sonnet 4.6 72.1% Робота з комп'ютером τ²-bench Gemini 3.0 Pro 85.3% Інструменти й агенти BFCL v4 (function calling) Claude Opus 4.5 77.5% Інструменти й агенти MMLU-Pro Gemini 3.1 Pro 91.2% Знання
Матриця «модель × бенчмарк»
У кожній клітинці — найкращий результат в основному налаштуванні (пріоритет — офіційні рейтинги та незалежні тести). ◇ — лише дані розробника або статті. Натисніть стовпець для сортування, позначте моделі для порівняння.
| Модель | 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% | — | — | — | — | — | — |
Усі бенчмарки
Програмування
LMArena WebDevАктивний Arena where two models each build a web app from the same prompt and users vote on the result. 127 моделей · Найкращий: 1813 LiveCodeBenchДавно не оновлювався 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 моделей · Найкращий: 75.8% HumanEval / HumanEval+Насичений 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 моделей · Найкращий: 89.0%
Мультимодальність
Загальне
Open LLM Leaderboard v2В архіві 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 моделей · Найкращий: 48.0% Artificial Analysis Intelligence IndexЛише посилання Independent composite index that runs a battery of evaluations plus price and speed measurements across API models. Лише посилання
Знання
MMLUНасичений About 14,000 multiple-choice questions over 57 subjects, from elementary maths to law and medicine. 158 моделей · Найкращий: 88.1% MMLU-ProАктивний Harder successor to MMLU: about 12,000 reasoning-heavy questions in 14 disciplines with 10 answer options. 243 моделей · Найкращий: 91.2% Humanity's Last ExamАктивний 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 моделей · Найкращий: 54.8%
Агентне програмування
SWE-bench VerifiedСпірний 500 human-validated GitHub issues from 12 Python repositories; the system must produce a patch that makes the hidden tests pass. 81 моделей · Найкращий: 83.5% SWE-bench ProЛише посилання Scale AI's harder, longer-horizon successor to SWE-bench with a 731-task public split and private/commercial splits. Лише посилання Terminal-Bench 2.0Активний Hard, realistic tasks an agent must finish in a sandboxed terminal (Stanford × Laude Institute). 45 моделей · Найкращий: 84.7%
Математика
AIME (OTIS Mock AIME 2024–2025)Активний 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 моделей · Найкращий: 100.0% MATH Level 5Насичений The hardest (level 5) problems of the MATH competition dataset (Hendrycks et al., 2021). 94 моделей · Найкращий: 98.1%
Абстрактне мислення
ARC-AGI-1Насичений Abstract grid puzzles (François Chollet) that test learning a new rule from a few examples. 6 моделей · Найкращий: 98.5% ARC-AGI-2Активний Harder second version of ARC-AGI (2025), designed so that brute-force search is not enough. 4 моделей · Найкращий: 95.0% ARC-AGI-3Активний Interactive, game-like third version of ARC-AGI that tests exploration and learning inside novel environments. 3 моделей · Найкращий: 99.9%
Робота з комп'ютером
OSWorld (Verified)Активний 369 real computer tasks in a full Ubuntu desktop (browsers, office apps, file manager, terminal) checked by execution-based scripts. 9 моделей · Найкращий: 72.1% OSWorld 2.0Активний Long-horizon successor to OSWorld (2026) with multi-application workflows. 9 моделей · Найкращий: 31.4%
Інструменти й агенти
τ²-benchАктивний 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 моделей · Найкращий: 85.3% BFCL v4 (function calling)Активний Berkeley Function Calling Leaderboard: single, parallel and multi-turn tool calls, web search, memory and relevance detection. 80 моделей · Найкращий: 77.5%
Китайська
CMMLUДавно не оновлювався Chinese multitask knowledge benchmark: 67 subjects including China-specific topics. 12 моделей · Найкращий: 90.3% C-EvalДавно не оновлювався Chinese evaluation suite of about 13,900 multiple-choice questions over 52 disciplines and four difficulty levels. 11 моделей · Найкращий: 68.7% SuperCLUEЛише посилання Periodic Chinese general-capability evaluation of domestic and international models, published as reports. Лише посилання
Як ми збираємо дані
- 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.
Тип джерела
- Офіційний рейтинг
- The benchmark maintainers' own leaderboard
- Незалежний тест
- An independent evaluator ran the model itself (e.g. Epoch AI)
- Дані розробника
- Self-reported or submitted by the model developer
- Стаття / техзвіт
- Reported in a paper or technical report (usually by the developer)
- Стороннє зведення
- Compiled by Epoch AI; the original source is not given per row
Джерела даних і ліцензії
| Джерело | Ліцензія / умови | Як ми використовуємо | Останній збір |
|---|---|---|---|
| LMArena leaderboard dataset LMArena, Arena Leaderboard Dataset (Hugging Face), CC BY 4.0 | CC BY 4.0 | Open licence – full data with attribution | 10 жовт. 2026 р. ⚠︎ |
| 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 жовт. 2026 р. |
| 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 жовт. 2026 р. |
| 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 жовт. 2026 р. |
| EvalPlus leaderboard EvalPlus team, evalplus.github.io | Apache-2.0 (site repo) | Open licence – full data with attribution | 22 жовт. 2026 р. |
| Berkeley Function Calling Leaderboard (BFCL) Gorilla / BFCL team, UC Berkeley | Apache-2.0 (gorilla repo) | Open licence – full data with attribution | 22 жовт. 2026 р. |
| τ²-bench leaderboard submissions Sierra Research, τ²-bench | MIT (repo) | Open licence – full data with attribution | 22 жовт. 2026 р. |
| MMLU-Pro leaderboard (TIGER-Lab) TIGER-Lab, MMLU-Pro leaderboard | Apache-2.0 (dataset) | Open licence – full data with attribution | 22 жовт. 2026 р. |
| 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 жовт. 2026 р. |
| 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 жовт. 2026 р. |
| 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 жовт. 2026 р. |
| 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 жовт. 2026 р. |
| 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 | — |
Для ШІ-агентів
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