Model rankings
288 models · 2 boards · 2 sources
Most preferred
Best open model
Best from China
Most voted
Top three by Score
chatgpt-4o-latest-20250326OpenAI1,359
gpt-4.5-preview-2025-02-27OpenAI1,356
grok-3-preview-02-24xAI1,328
Top three open models
deepseek-v3-0324DeepSeek · #5 overall1,319
deepseek-r1DeepSeek · #7 overall1,315
gemma-3-27b-itGoogle · #14 overall1,279
This week's changes
Llama 3.3 Nemotron Super 49B v1Intelligence · #29New
Grok 2 (Dec '24)Intelligence · #30New
Mistral Small 3.1Intelligence · #41New
Gemini 1.5 Flash-8BIntelligence · #50New
Gemma 2 9BIntelligence · #71New
| Rank | Change | Model | Score | 95% interval | Votes | Price $/M |
|---|---|---|---|---|---|---|
| 1 | ▲ 2 | deepseek-v3-0324OpenDeepSeek · 1 more variant | 1,319 | ±9 | 2,840 | — |
| 2 | ▼ 1 | deepseek-r1OpenDeepSeek | 1,315 | ±5 | 13,836 | — |
| 3 | ▼ 1 | qwen2.5-maxClosedAlibaba | 1,285 | ±4 | 18,332 | — |
| 4 | — | hunyuan-turbos-20250226ClosedTencent | 1,264 | ±12 | 2,453 | — |
| 5 | — | qwen-plus-0125ClosedAlibaba | 1,262 | ±7 | 6,057 | — |
| 6 | — | hunyuan-turbo-0110ClosedTencent | 1,258 | ±11 | 2,511 | — |
| 7 | ▲ 1 | qwq-32bOpenAlibaba · 1 more variant | 1,257 | ±8 | 5,167 | — |
| 8 | ▼ 1 | glm-4-plus-0111ClosedZhipu · 1 more variant | 1,256 | ±6 | 6,036 | — |
| 9 | — | step-2-16k-exp-202412ClosedStepFun | 1,251 | ±7 | 5,128 | — |
| 10 | — | yi-lightningClosed01 AI | 1,246 | ±4 | 28,970 | — |
| 11 | — | hunyuan-large-2025-02-10ClosedTencent | 1,242 | ±8 | 3,863 | — |
| 12 | — | deepseek-v2.5-1210OpenDeepSeek · 1 more variant | 1,240 | ±5 | 7,248 | — |
| 13 | ▲ 1 | qwen-max-0919OpenAlibaba | 1,231 | ±4 | 17,430 | — |
| 14 | ▼ 1 | qwen2.5-plus-1127ClosedAlibaba | 1,231 | ±6 | 10,715 | — |
| 15 | — | hunyuan-standard-2025-02-10ClosedTencent | 1,228 | ±7 | 4,015 | — |
| 16 | — | qwen2.5-72b-instructOpenAlibaba | 1,222 | ±3 | 41,538 | — |
| 17 | — | qwen2.5-coder-32b-instructOpenAlibaba | 1,189 | ±7 | 5,731 | — |
| 18 | — | glm-4-0520ClosedZhipu AI | 1,188 | ±5 | 10,218 | — |
| 19 | — | deepseek-coder-v2OpenDeepSeek | 1,182 | ±4 | 15,752 | — |
| 20 | — | qwen2-72b-instructOpenAlibaba | 1,180 | ±3 | 38,893 | — |
| 21 | — | qwen1.5-110b-chatOpenAlibaba | 1,155 | ±4 | 27,436 | — |
| 22 | — | hunyuan-standard-256kClosedTencent | 1,152 | ±12 | 2,902 | — |
| 23 | — | qwen1.5-72b-chatOpenAlibaba | 1,148 | ±3 | 40,667 | — |
| 24 | — | yi-1.5-34b-chatOpen01 AI | 1,133 | ±4 | 25,137 | — |
| 25 | — | qwen1.5-32b-chatOpenAlibaba | 1,126 | ±4 | 22,772 | — |
| 26 | — | qwen1.5-14b-chatOpenAlibaba | 1,107 | ±4 | 18,691 | — |
| 27 | — | yi-34b-chatOpen01 AI | 1,101 | ±4 | 15,919 | — |
| 28 | — | deepseek-llm-67b-chatOpenDeepSeek | 1,091 | ±9 | 4,988 | — |
| 29 | — | qwen1.5-7b-chatOpenAlibaba | 1,065 | ±7 | 4,871 | — |
| 30 | — | qwen-14b-chatOpenAlibaba | 1,056 | ±8 | 5,067 | — |
| 31 | — | qwen1.5-4b-chatOpenAlibaba | 1,015 | ±7 | 7,825 | — |
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