Model rankings
391 models · 2 boards · 2 sources
Most preferred
Best open model
Best from China
Most voted
Top three by Score
o3-2025-04-16OpenAI1,442
chatgpt-4o-latest-20250326OpenAI1,429
gpt-4.5-preview-2025-02-27OpenAI1,424
Top three open models
deepseek-v3-0324DeepSeek · #10 overall1,386
deepseek-r1DeepSeek · #11 overall1,382
gemma-3-27b-itGoogle · #22 overall1,351
This week's changes
Claude 4 Sonnet (Extended Thinking)Intelligence · #10New
Claude 4 OpusIntelligence · #14New
Grok 3 Reasoning BetaIntelligence · #16New
o1-proIntelligence · #16New
GPT-4.5 (Preview)Intelligence · #22New
| Rank | Change | Model | Score | 95% interval | Votes | Price $/M |
|---|---|---|---|---|---|---|
| 1 | — | deepseek-v3-0324OpenDeepSeek · 1 more variant | 1,386 | ±5 | 14,408 | — |
| 2 | — | deepseek-r1OpenDeepSeek | 1,382 | ±4 | 19,430 | — |
| 3 | — | hunyuan-turbos-20250416ClosedTencent · 1 more variant | 1,362 | ±7 | 5,230 | — |
| 4 | — | qwen2.5-maxClosedAlibaba | 1,356 | ±3 | 28,067 | — |
| 5 | — | qwen3-235b-a22bOpenAlibaba | 1,340 | ±6 | 8,707 | — |
| 6 | ▲ 1 | qwen-plus-0125ClosedAlibaba | 1,330 | ±7 | 6,055 | — |
| 7 | ▲ 1 | hunyuan-turbo-0110ClosedTencent | 1,326 | ±9 | 2,510 | — |
| 8 | ▲ 1 | glm-4-plus-0111ClosedZhipu · 1 more variant | 1,324 | ±6 | 6,028 | — |
| 9 | ▲ 2 | step-2-16k-exp-202412ClosedStepFun | 1,319 | ±7 | 5,126 | — |
| 10 | ▲ 2 | yi-lightningClosed01 AI | 1,314 | ±3 | 28,968 | — |
| 11 | ▲ 2 | hunyuan-large-2025-02-10ClosedTencent | 1,309 | ±6 | 3,856 | — |
| 12 | ▼ 2 | qwq-32bOpenAlibaba · 1 more variant | 1,308 | ±4 | 14,606 | — |
| 13 | ▲ 1 | deepseek-v2.5-1210OpenDeepSeek · 1 more variant | 1,308 | ±6 | 7,243 | — |
| 14 | ▲ 2 | qwen2.5-plus-1127ClosedAlibaba | 1,299 | ±5 | 10,715 | — |
| 15 | ▲ 2 | qwen-max-0919OpenAlibaba | 1,299 | ±4 | 17,432 | — |
| 16 | ▲ 2 | hunyuan-standard-2025-02-10ClosedTencent | 1,297 | ±9 | 4,014 | — |
| 17 | ▲ 2 | qwen2.5-72b-instructOpenAlibaba | 1,290 | ±3 | 41,519 | — |
| 18 | ▲ 2 | qwen2.5-coder-32b-instructOpenAlibaba | 1,257 | ±8 | 5,730 | — |
| 19 | ▲ 2 | glm-4-0520ClosedZhipu AI | 1,256 | ±6 | 10,221 | — |
| 20 | ▲ 2 | deepseek-coder-v2OpenDeepSeek | 1,249 | ±5 | 15,753 | — |
| 21 | ▲ 2 | qwen2-72b-instructOpenAlibaba | 1,248 | ±3 | 38,872 | — |
| 22 | ▲ 2 | qwen1.5-110b-chatOpenAlibaba | 1,223 | ±3 | 27,430 | — |
| 23 | ▲ 2 | hunyuan-standard-256kClosedTencent | 1,220 | ±11 | 2,901 | — |
| 24 | ▲ 2 | qwen1.5-72b-chatOpenAlibaba | 1,215 | ±3 | 40,658 | — |
| 25 | ▲ 2 | yi-1.5-34b-chatOpen01 AI | 1,201 | ±3 | 25,135 | — |
| 26 | ▲ 2 | qwen1.5-32b-chatOpenAlibaba | 1,194 | ±3 | 22,765 | — |
| 27 | ▲ 2 | qwen1.5-14b-chatOpenAlibaba | 1,174 | ±4 | 18,687 | — |
| 28 | ▲ 2 | yi-34b-chatOpen01 AI | 1,168 | ±5 | 15,917 | — |
| 29 | ▲ 2 | deepseek-llm-67b-chatOpenDeepSeek | 1,158 | ±8 | 4,988 | — |
| 30 | ▲ 2 | qwen1.5-7b-chatOpenAlibaba | 1,132 | ±7 | 4,872 | — |
| 31 | ▲ 2 | qwen-14b-chatOpenAlibaba | 1,124 | ±8 | 5,065 | — |
| 32 | ▲ 2 | qwen1.5-4b-chatOpenAlibaba | 1,082 | ±6 | 7,816 | — |
Intelligence over time
Gained most · Anthropic +57.2Highest now · Anthropic 64.6Gap between highest and lowest 18.1 ptsTime range Nov 2025 – Nov 2026
64.6Anthropic60.0Google56.9OpenAI50.1Meta46.5Kimi