Model rankings
340 models · 2 boards · 2 sources
Most preferred
Best open model
Best from China
Most voted
Top three by Score
o3-2025-04-16OpenAI1,375
chatgpt-4o-latest-20250326OpenAI1,362
gpt-4.5-preview-2025-02-27OpenAI1,357
Top three open models
deepseek-v3-0324DeepSeek · #7 overall1,323
deepseek-r1DeepSeek · #9 overall1,316
qwen3-235b-a22bAlibaba · #18 overall1,286
This week's changes
Qwen3 8B (Reasoning)Intelligence · #22New
Mistral Medium 3Intelligence · #29New
Qwen3 4B (Reasoning)Intelligence · #32New
Qwen3 1.7B (Reasoning)Intelligence · #54New
Qwen3 0.6B (Reasoning)Intelligence · #95New
| Rank | Change | Model | Score | 95% interval | Votes | Price $/M |
|---|---|---|---|---|---|---|
| 1 | — | deepseek-v3-0324OpenDeepSeek · 1 more variant | 1,323 | ±6 | 8,753 | — |
| 2 | — | deepseek-r1OpenDeepSeek | 1,316 | ±4 | 18,493 | — |
| 3 | — | hunyuan-turbos-20250416ClosedTencent · 1 more variant | 1,295 | ±10 | 3,699 | — |
| 4 | — | qwen2.5-maxClosedAlibaba | 1,286 | ±4 | 23,180 | — |
| 5 | — | qwen3-235b-a22bOpenAlibaba | 1,286 | ±9 | 3,611 | — |
| 6 | — | qwen-plus-0125ClosedAlibaba | 1,263 | ±7 | 6,058 | — |
| 7 | — | hunyuan-turbo-0110ClosedTencent | 1,259 | ±11 | 2,512 | — |
| 8 | — | glm-4-plus-0111ClosedZhipu · 1 more variant | 1,257 | ±7 | 6,024 | — |
| 9 | — | qwq-32bOpenAlibaba · 1 more variant | 1,256 | ±5 | 9,946 | — |
| 10 | — | step-2-16k-exp-202412ClosedStepFun | 1,252 | ±7 | 5,125 | — |
| 11 | — | yi-lightningClosed01 AI | 1,247 | ±3 | 28,968 | — |
| 12 | — | hunyuan-large-2025-02-10ClosedTencent | 1,242 | ±9 | 3,858 | — |
| 13 | — | deepseek-v2.5-1210OpenDeepSeek · 1 more variant | 1,241 | ±5 | 7,242 | — |
| 14 | — | qwen2.5-plus-1127ClosedAlibaba | 1,232 | ±4 | 10,711 | — |
| 15 | — | qwen-max-0919OpenAlibaba | 1,232 | ±4 | 17,432 | — |
| 16 | — | hunyuan-standard-2025-02-10ClosedTencent | 1,230 | ±9 | 4,015 | — |
| 17 | — | qwen2.5-72b-instructOpenAlibaba | 1,223 | ±2 | 41,517 | — |
| 18 | — | qwen2.5-coder-32b-instructOpenAlibaba | 1,190 | ±7 | 5,733 | — |
| 19 | — | glm-4-0520ClosedZhipu AI | 1,189 | ±5 | 10,224 | — |
| 20 | — | deepseek-coder-v2OpenDeepSeek | 1,182 | ±4 | 15,756 | — |
| 21 | — | qwen2-72b-instructOpenAlibaba | 1,181 | ±3 | 38,870 | — |
| 22 | — | qwen1.5-110b-chatOpenAlibaba | 1,155 | ±4 | 27,438 | — |
| 23 | — | hunyuan-standard-256kClosedTencent | 1,153 | ±11 | 2,900 | — |
| 24 | — | qwen1.5-72b-chatOpenAlibaba | 1,148 | ±3 | 40,665 | — |
| 25 | — | yi-1.5-34b-chatOpen01 AI | 1,134 | ±3 | 25,136 | — |
| 26 | — | qwen1.5-32b-chatOpenAlibaba | 1,126 | ±4 | 22,762 | — |
| 27 | — | qwen1.5-14b-chatOpenAlibaba | 1,107 | ±4 | 18,685 | — |
| 28 | — | yi-34b-chatOpen01 AI | 1,101 | ±4 | 15,918 | — |
| 29 | — | deepseek-llm-67b-chatOpenDeepSeek | 1,091 | ±8 | 4,988 | — |
| 30 | — | qwen1.5-7b-chatOpenAlibaba | 1,065 | ±8 | 4,873 | — |
| 31 | — | qwen-14b-chatOpenAlibaba | 1,056 | ±9 | 5,067 | — |
| 32 | — | qwen1.5-4b-chatOpenAlibaba | 1,014 | ±7 | 7,819 | — |
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