LMArena · GPQA · SWE-bench · HLE · ARC-AGI · OSWorld · BFCL
AI 모델 평가
1079개 모델, 23개 벤치마크, 3086개 점수. 모든 수치는 출처로 연결되며 업체 자체 보고는 따로 표시합니다.
점수 3086개 모델 1079개 벤치마크 23개 2026년 10월 22일 업데이트
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 인간 선호 GPQA Diamond Gemini 4 Argon 96.4% 과학 Humanity's Last Exam GPT-6 Astra 54.8% 지식 AIME (OTIS Mock AIME 2024–2025) Gemini 4 Argon 100.0% 수학 SWE-bench Verified Claude Opus 4.7 83.5% 에이전트 코딩 Terminal-Bench 2.0 GPT-5.5 84.7% 에이전트 코딩 OSWorld (Verified) Claude Sonnet 4.6 72.1% 컴퓨터 사용 τ²-bench Gemini 3.0 Pro 85.3% 도구 사용·에이전트 BFCL v4 (function calling) Claude Opus 4.5 77.5% 도구 사용·에이전트 MMLU-Pro Gemini 3.1 Pro 91.2% 지식
모델 × 벤치마크 표
각 칸은 기본 설정에서의 최고 점수입니다(공식 리더보드·독립 평가 우선). ◇는 업체 자체 보고 또는 논문 수치만 있음. 열 이름을 눌러 정렬, 체크해서 비교.
| 모델 | 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% | — | — | — | — | — | — |
전체 벤치마크
코딩
LMArena WebDev업데이트 중 Arena where two models each build a web app from the same prompt and users vote on the result. 모델 127개 · 최고: 1813 LiveCodeBench최근 업데이트 없음 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. 모델 22개 · 최고: 75.8% HumanEval / HumanEval+포화 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. 모델 122개 · 최고: 89.0%
종합
Open LLM Leaderboard v2보관됨 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. 모델 294개 · 최고: 48.0% Artificial Analysis Intelligence Index링크만 Independent composite index that runs a battery of evaluations plus price and speed measurements across API models. 링크만
지식
MMLU포화 About 14,000 multiple-choice questions over 57 subjects, from elementary maths to law and medicine. 모델 158개 · 최고: 88.1% MMLU-Pro업데이트 중 Harder successor to MMLU: about 12,000 reasoning-heavy questions in 14 disciplines with 10 answer options. 모델 243개 · 최고: 91.2% Humanity's Last Exam업데이트 중 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. 모델 46개 · 최고: 54.8%
에이전트 코딩
SWE-bench Verified논란 있음 500 human-validated GitHub issues from 12 Python repositories; the system must produce a patch that makes the hidden tests pass. 모델 81개 · 최고: 83.5% SWE-bench Pro링크만 Scale AI's harder, longer-horizon successor to SWE-bench with a 731-task public split and private/commercial splits. 링크만 Terminal-Bench 2.0업데이트 중 Hard, realistic tasks an agent must finish in a sandboxed terminal (Stanford × Laude Institute). 모델 45개 · 최고: 84.7%
수학
AIME (OTIS Mock AIME 2024–2025)업데이트 중 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. 모델 200개 · 최고: 100.0% MATH Level 5포화 The hardest (level 5) problems of the MATH competition dataset (Hendrycks et al., 2021). 모델 94개 · 최고: 98.1%
추상 추론
ARC-AGI-1포화 Abstract grid puzzles (François Chollet) that test learning a new rule from a few examples. 모델 6개 · 최고: 98.5% ARC-AGI-2업데이트 중 Harder second version of ARC-AGI (2025), designed so that brute-force search is not enough. 모델 4개 · 최고: 95.0% ARC-AGI-3업데이트 중 Interactive, game-like third version of ARC-AGI that tests exploration and learning inside novel environments. 모델 3개 · 최고: 99.9%
컴퓨터 사용
도구 사용·에이전트
τ²-bench업데이트 중 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). 모델 43개 · 최고: 85.3% BFCL v4 (function calling)업데이트 중 Berkeley Function Calling Leaderboard: single, parallel and multi-turn tool calls, web search, memory and relevance detection. 모델 80개 · 최고: 77.5%
중국어
CMMLU최근 업데이트 없음 Chinese multitask knowledge benchmark: 67 subjects including China-specific topics. 모델 12개 · 최고: 90.3% C-Eval최근 업데이트 없음 Chinese evaluation suite of about 13,900 multiple-choice questions over 52 disciplines and four difficulty levels. 모델 11개 · 최고: 68.7% SuperCLUE링크만 Periodic Chinese general-capability evaluation of domestic and international models, published as reports. 링크만
수집 방법
- 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.
출처 유형
- 공식 리더보드
- The benchmark maintainers' own leaderboard
- 독립 평가
- An independent evaluator ran the model itself (e.g. Epoch AI)
- 업체 자체 보고
- Self-reported or submitted by the model developer
- 논문 / 기술 보고서
- Reported in a paper or technical report (usually by the developer)
- 제3자 취합
- Compiled by Epoch AI; the original source is not given per row
데이터 출처와 라이선스
| 출처 | 라이선스 / 약관 | 사이트 이용 방식 | 최근 수집 |
|---|---|---|---|
| LMArena leaderboard dataset LMArena, Arena Leaderboard Dataset (Hugging Face), CC BY 4.0 | CC BY 4.0 | Open licence – full data with attribution | 2026년 10월 10일 ⚠︎ |
| 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 | 2026년 10월 22일 |
| 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 | 2026년 10월 22일 |
| 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 | 2026년 10월 22일 |
| EvalPlus leaderboard EvalPlus team, evalplus.github.io | Apache-2.0 (site repo) | Open licence – full data with attribution | 2026년 10월 22일 |
| Berkeley Function Calling Leaderboard (BFCL) Gorilla / BFCL team, UC Berkeley | Apache-2.0 (gorilla repo) | Open licence – full data with attribution | 2026년 10월 22일 |
| τ²-bench leaderboard submissions Sierra Research, τ²-bench | MIT (repo) | Open licence – full data with attribution | 2026년 10월 22일 |
| MMLU-Pro leaderboard (TIGER-Lab) TIGER-Lab, MMLU-Pro leaderboard | Apache-2.0 (dataset) | Open licence – full data with attribution | 2026년 10월 22일 |
| 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 | 2026년 10월 22일 |
| 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) | 2026년 10월 22일 |
| 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 | 2026년 10월 22일 |
| 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 | 2026년 10월 22일 |
| 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 | — |
AI 에이전트용
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