Model rankings
124 models · 1 boards · 1 sources
Most preferred
Best open model
Best from China
Most voted
Top three open models
llama-3.1-405b-instruct-bf16Meta · #7 overall1,252
llama-3.1-405b-instruct-fp8Meta · #8 overall1,251
mistral-large-2407Mistral · #16 overall1,230
| Rank | Change | Model | Score | 95% interval | Votes | Price $/M |
|---|---|---|---|---|---|---|
| 1 | — | qwen2.5-72b-instructOpenAlibaba | 1,218 | ±6 | 11,306 | — |
| 2 | — | deepseek-v2.5OpenDeepSeek | 1,217 | ±6 | 11,330 | — |
| 3 | — | glm-4-0520ClosedZhipu AI | 1,187 | ±6 | 10,229 | — |
| 4 | ▲ 1 | deepseek-coder-v2OpenDeepSeek | 1,181 | ±5 | 15,791 | — |
| 5 | ▼ 1 | qwen2-72b-instructOpenAlibaba | 1,180 | ±3 | 38,973 | — |
| 6 | — | qwen1.5-110b-chatOpenAlibaba | 1,155 | ±4 | 27,442 | — |
| 7 | — | qwen1.5-72b-chatOpenAlibaba | 1,147 | ±4 | 40,610 | — |
| 8 | — | yi-1.5-34b-chatOpen01 AI | 1,131 | ±4 | 25,141 | — |
| 9 | — | qwen1.5-32b-chatOpenAlibaba | 1,126 | ±4 | 22,738 | — |
| 10 | — | qwen1.5-14b-chatOpenAlibaba | 1,106 | ±4 | 18,656 | — |
| 11 | — | yi-34b-chatOpen01 AI | 1,101 | ±5 | 15,918 | — |
| 12 | — | deepseek-llm-67b-chatOpenDeepSeek | 1,091 | ±8 | 4,979 | — |
| 13 | — | qwen1.5-7b-chatOpenAlibaba | 1,066 | ±10 | 4,861 | — |
| 14 | — | qwen-14b-chatOpenAlibaba | 1,057 | ±9 | 5,068 | — |
| 15 | — | qwen1.5-4b-chatOpenAlibaba | 1,014 | ±7 | 7,805 | — |
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