Model rankings
347 models · 2 boards · 2 sources
Most preferred
Best open model
Best from China
Most voted
Top three by Score
o3-2025-04-16OpenAI1,435
chatgpt-4o-latest-20250326OpenAI1,422
gpt-4.5-preview-2025-02-27OpenAI1,417
Top three open models
deepseek-v3-0324DeepSeek · #6 overall1,382
deepseek-r1DeepSeek · #9 overall1,376
qwen3-235b-a22bAlibaba · #20 overall1,343
This week's changes
Qwen2.5 TurboIntelligence · #70New
| Rank | Change | Model | Score | 95% interval | Votes | Price $/M |
|---|---|---|---|---|---|---|
| 1 | — | deepseek-v3-0324OpenDeepSeek · 1 more variant | 1,382 | ±5 | 9,741 | — |
| 2 | — | deepseek-r1OpenDeepSeek | 1,376 | ±4 | 19,339 | — |
| 3 | — | hunyuan-turbos-20250416ClosedTencent · 1 more variant | 1,359 | ±8 | 5,111 | — |
| 4 | — | qwen2.5-maxClosedAlibaba | 1,346 | ±4 | 23,170 | — |
| 5 | — | qwen3-235b-a22bOpenAlibaba | 1,343 | ±9 | 4,942 | — |
| 6 | New | qwen3-32bOpenAlibaba | 1,328 | ±9 | 3,960 | — |
| 7 | ▼ 1 | qwen-plus-0125ClosedAlibaba | 1,323 | ±7 | 6,056 | — |
| 8 | ▼ 1 | hunyuan-turbo-0110ClosedTencent | 1,320 | ±10 | 2,513 | — |
| 9 | ▼ 1 | glm-4-plus-0111ClosedZhipu · 1 more variant | 1,317 | ±8 | 6,028 | — |
| 10 | ▼ 1 | qwq-32bOpenAlibaba · 1 more variant | 1,316 | ±5 | 9,936 | — |
| 11 | ▼ 1 | step-2-16k-exp-202412ClosedStepFun | 1,312 | ±8 | 5,128 | — |
| 12 | ▼ 1 | yi-lightningClosed01 AI | 1,307 | ±4 | 28,971 | — |
| 13 | ▼ 1 | hunyuan-large-2025-02-10ClosedTencent | 1,302 | ±9 | 3,858 | — |
| 14 | ▼ 1 | deepseek-v2.5-1210OpenDeepSeek · 1 more variant | 1,301 | ±7 | 7,245 | — |
| 15 | New | qwen3-30b-a3bOpenAlibaba | 1,295 | ±9 | 4,159 | — |
| 16 | ▼ 2 | qwen2.5-plus-1127ClosedAlibaba | 1,292 | ±5 | 10,714 | — |
| 17 | ▼ 2 | qwen-max-0919OpenAlibaba | 1,292 | ±5 | 17,431 | — |
| 18 | ▼ 2 | hunyuan-standard-2025-02-10ClosedTencent | 1,290 | ±8 | 4,013 | — |
| 19 | ▼ 2 | qwen2.5-72b-instructOpenAlibaba | 1,283 | ±2 | 41,520 | — |
| 20 | ▼ 2 | qwen2.5-coder-32b-instructOpenAlibaba | 1,250 | ±7 | 5,731 | — |
| 21 | ▼ 2 | glm-4-0520ClosedZhipu AI | 1,249 | ±5 | 10,222 | — |
| 22 | ▼ 2 | deepseek-coder-v2OpenDeepSeek | 1,242 | ±4 | 15,753 | — |
| 23 | ▼ 2 | qwen2-72b-instructOpenAlibaba | 1,240 | ±2 | 38,873 | — |
| 24 | ▼ 2 | qwen1.5-110b-chatOpenAlibaba | 1,215 | ±3 | 27,431 | — |
| 25 | ▼ 2 | hunyuan-standard-256kClosedTencent | 1,213 | ±10 | 2,900 | — |
| 26 | ▼ 2 | qwen1.5-72b-chatOpenAlibaba | 1,208 | ±3 | 40,655 | — |
| 27 | ▼ 2 | yi-1.5-34b-chatOpen01 AI | 1,193 | ±3 | 25,136 | — |
| 28 | ▼ 2 | qwen1.5-32b-chatOpenAlibaba | 1,186 | ±4 | 22,765 | — |
| 29 | ▼ 2 | qwen1.5-14b-chatOpenAlibaba | 1,167 | ±4 | 18,682 | — |
| 30 | ▼ 2 | yi-34b-chatOpen01 AI | 1,161 | ±4 | 15,916 | — |
| 31 | ▼ 2 | deepseek-llm-67b-chatOpenDeepSeek | 1,151 | ±7 | 4,988 | — |
| 32 | ▼ 2 | qwen1.5-7b-chatOpenAlibaba | 1,125 | ±7 | 4,872 | — |
| 33 | ▼ 2 | qwen-14b-chatOpenAlibaba | 1,116 | ±8 | 5,065 | — |
| 34 | ▼ 2 | qwen1.5-4b-chatOpenAlibaba | 1,074 | ±7 | 7,818 | — |
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