Model rankings
398 models · 2 boards · 2 sources
Most preferred
Best open model
Best from China
Most voted
Top three by Score
o3-2025-04-16OpenAI1,447
chatgpt-4o-latest-20250326OpenAI1,436
gpt-4.5-preview-2025-02-27OpenAI1,430
Top three open models
deepseek-v3-0324DeepSeek · #9 overall1,394
deepseek-r1DeepSeek · #11 overall1,388
gemma-3-27b-itGoogle · #22 overall1,357
This week's changes
o3-proIntelligence · #1New
DeepSeek R1 0528 Qwen3 8BIntelligence · #27New
Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)Intelligence · #43New
| Rank | Change | Model | Score | 95% interval | Votes | Price $/M |
|---|---|---|---|---|---|---|
| 1 | — | deepseek-v3-0324OpenDeepSeek · 1 more variant | 1,394 | ±4 | 16,550 | — |
| 2 | — | deepseek-r1OpenDeepSeek | 1,388 | ±4 | 19,430 | — |
| 3 | — | hunyuan-turbos-20250416ClosedTencent · 1 more variant | 1,370 | ±7 | 5,944 | — |
| 4 | — | qwen2.5-maxClosedAlibaba | 1,363 | ±3 | 29,484 | — |
| 5 | — | qwen3-235b-a22bOpenAlibaba | 1,342 | ±6 | 10,677 | — |
| 6 | — | qwen-plus-0125ClosedAlibaba | 1,336 | ±7 | 6,055 | — |
| 7 | — | hunyuan-turbo-0110ClosedTencent | 1,332 | ±11 | 2,510 | — |
| 8 | — | glm-4-plus-0111ClosedZhipu · 1 more variant | 1,330 | ±6 | 6,028 | — |
| 9 | — | step-2-16k-exp-202412ClosedStepFun | 1,325 | ±7 | 5,126 | — |
| 10 | — | yi-lightningClosed01 AI | 1,320 | ±3 | 28,968 | — |
| 11 | — | hunyuan-large-2025-02-10ClosedTencent | 1,316 | ±9 | 3,856 | — |
| 12 | ▲ 1 | deepseek-v2.5-1210OpenDeepSeek · 1 more variant | 1,314 | ±6 | 7,243 | — |
| 13 | ▼ 1 | qwq-32bOpenAlibaba · 1 more variant | 1,313 | ±5 | 15,930 | — |
| 14 | — | qwen2.5-plus-1127ClosedAlibaba | 1,305 | ±5 | 10,715 | — |
| 15 | — | qwen-max-0919OpenAlibaba | 1,305 | ±4 | 17,432 | — |
| 16 | — | hunyuan-standard-2025-02-10ClosedTencent | 1,303 | ±9 | 4,014 | — |
| 17 | — | qwen2.5-72b-instructOpenAlibaba | 1,296 | ±2 | 41,519 | — |
| 18 | — | qwen2.5-coder-32b-instructOpenAlibaba | 1,264 | ±7 | 5,730 | — |
| 19 | — | glm-4-0520ClosedZhipu AI | 1,262 | ±5 | 10,221 | — |
| 20 | — | deepseek-coder-v2OpenDeepSeek | 1,256 | ±4 | 15,753 | — |
| 21 | — | qwen2-72b-instructOpenAlibaba | 1,254 | ±3 | 38,872 | — |
| 22 | — | qwen1.5-110b-chatOpenAlibaba | 1,229 | ±3 | 27,430 | — |
| 23 | — | hunyuan-standard-256kClosedTencent | 1,226 | ±10 | 2,901 | — |
| 24 | — | qwen1.5-72b-chatOpenAlibaba | 1,221 | ±3 | 40,658 | — |
| 25 | — | yi-1.5-34b-chatOpen01 AI | 1,207 | ±3 | 25,135 | — |
| 26 | — | qwen1.5-32b-chatOpenAlibaba | 1,200 | ±3 | 22,765 | — |
| 27 | — | qwen1.5-14b-chatOpenAlibaba | 1,180 | ±4 | 18,687 | — |
| 28 | — | yi-34b-chatOpen01 AI | 1,174 | ±5 | 15,917 | — |
| 29 | — | deepseek-llm-67b-chatOpenDeepSeek | 1,164 | ±7 | 4,988 | — |
| 30 | — | qwen1.5-7b-chatOpenAlibaba | 1,138 | ±7 | 4,872 | — |
| 31 | — | qwen-14b-chatOpenAlibaba | 1,130 | ±7 | 5,065 | — |
| 32 | — | qwen1.5-4b-chatOpenAlibaba | 1,088 | ±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