Model rankings
443 models · 2 boards · 2 sources
Most preferred
Best open model
Best from China
Most voted
Top three by Score
gemini-2.5-proGoogle1,460
o3-2025-04-16OpenAI1,452
chatgpt-4o-latest-20250326OpenAI1,443
Top three open models
kimi-k2-0711-previewMoonshot AI · #6 overall1,418
deepseek-r1-0528DeepSeek · #8 overall1,416
qwen3-235b-a22b-no-thinkingAlibaba · #14 overall1,398
This week's changes
Kimi K2Intelligence · #22New
Claude 4 Sonnet (Extended Thinking)Intelligence · #13Up 4
| Rank | Change | Model | Score | 95% interval | Votes | Price $/M |
|---|---|---|---|---|---|---|
| 1 | — | kimi-k2-0711-previewOpenMoonshot AI | 1,418 | ±7 | 7,373 | — |
| 2 | — | deepseek-r1-0528OpenDeepSeek · 1 more variant | 1,416 | ±6 | 16,047 | — |
| 3 | — | qwen3-235b-a22b-no-thinkingOpenAlibaba | 1,398 | ±5 | 21,872 | — |
| 4 | — | deepseek-v3-0324OpenDeepSeek · 1 more variant | 1,393 | ±5 | 24,802 | — |
| 5 | — | minimax-m1OpenMiniMax | 1,376 | ±6 | 14,013 | — |
| 6 | — | qwen3-235b-a22bOpenAlibaba | 1,371 | ±6 | 18,128 | — |
| 7 | — | gemma-3-27b-itOpenGoogle | 1,362 | ±5 | 29,689 | — |
| 8 | — | mistral-small-2506OpenMistral | 1,350 | ±8 | 6,642 | — |
| 9 | — | qwen3-32bOpenAlibaba | 1,346 | ±9 | 4,074 | — |
| 10 | — | command-a-03-2025OpenCohere | 1,346 | ±5 | 28,366 | — |
| 11 | — | llama-3.1-nemotron-ultra-253b-v1OpenNVIDIA | 1,344 | ±12 | 2,656 | — |
| 12 | — | gemma-3-12b-itOpenGoogle | 1,340 | ±9 | 3,976 | — |
| 13 | ▲ 1 | llama-3.1-405b-instruct-bf16OpenMeta | 1,334 | ±4 | 43,788 | — |
| 14 | ▼ 1 | qwq-32bOpenAlibaba · 1 more variant | 1,334 | ±5 | 20,336 | — |
| 15 | — | llama-3.1-405b-instruct-fp8OpenMeta | 1,333 | ±3 | 63,038 | — |
| 16 | — | llama-4-maverick-17b-128e-instructOpenMeta | 1,330 | ±5 | 21,923 | — |
| 17 | — | qwen3-30b-a3bOpenAlibaba | 1,329 | ±6 | 17,951 | — |
| 18 | — | llama-3.3-nemotron-49b-super-v1OpenNVIDIA | 1,324 | ±12 | 2,371 | — |
| 19 | ▲ 1 | deepseek-v2.5-1210OpenDeepSeek · 1 more variant | 1,321 | ±8 | 7,243 | — |
| 20 | ▼ 1 | llama-4-scout-17b-16e-instructOpenMeta | 1,316 | ±7 | 11,604 | — |
| 21 | — | llama-3.3-70b-instructOpenMeta | 1,316 | ±4 | 49,882 | — |
| 22 | ▲ 2 | qwen-max-0919OpenAlibaba | 1,316 | ±5 | 17,432 | — |
| 23 | ▼ 1 | gemma-3n-e4b-itOpenGoogle | 1,313 | ±7 | 10,827 | — |
| 24 | ▲ 1 | athene-v2-chatOpenNexusFlow | 1,313 | ±4 | 26,074 | — |
| 25 | ▼ 2 | mistral-large-2407OpenMistral · 1 more variant | 1,312 | ±4 | 48,217 | — |
| 26 | — | athene-70b-0725OpenNexusFlow | 1,304 | ±5 | 20,580 | — |
| 27 | — | gemma-3-4b-itOpenGoogle | 1,303 | ±9 | 4,321 | — |
| 28 | — | qwen2.5-72b-instructOpenAlibaba | 1,301 | ±4 | 41,519 | — |
| 29 | — | llama-3.1-nemotron-70b-instructOpenNVIDIA | 1,297 | ±8 | 7,577 | — |
| 30 | ▲ 1 | llama-3.1-70b-instructOpenMeta | 1,294 | ±4 | 58,637 | — |
| 31 | ▼ 1 | mistral-small-3.1-24b-instruct-2503OpenMistral | 1,291 | ±7 | 11,493 | — |
| 32 | — | llama-3.1-tulu-3-70bOpenAi2 | 1,288 | ±10 | 3,010 | — |
| 33 | ▲ 1 | jamba-1.5-largeOpenAI21 Labs | 1,288 | ±7 | 9,125 | — |
| 34 | ▲ 1 | llama-3.1-nemotron-51b-instructOpenNVIDIA | 1,286 | ±10 | 3,889 | — |
| 35 | ▼ 2 | gemma-2-27b-itOpenGoogle | 1,285 | ±3 | 79,538 | — |
| 36 | ▲ 2 | nemotron-4-340b-instructOpenNVIDIA | 1,279 | ±5 | 20,608 | — |
| 37 | ▼ 1 | gemma-2-9b-it-simpoOpenPrinceton | 1,279 | ±7 | 10,548 | — |
| 38 | ▼ 1 | command-r-plus-08-2024OpenCohere | 1,279 | ±6 | 10,535 | — |
| 39 | — | llama-3-70b-instructOpenMeta | 1,275 | ±3 | 163,629 | — |
| 40 | — | mistral-small-24b-instruct-2501OpenMistral | 1,275 | ±6 | 15,321 | — |
| 41 | — | qwen2.5-coder-32b-instructOpenAlibaba | 1,271 | ±8 | 5,730 | — |
| 42 | — | c4ai-aya-expanse-32bOpenCohere | 1,268 | ±5 | 28,768 | — |
| 43 | — | command-r-plusOpenCohere | 1,265 | ±4 | 80,846 | — |
| 44 | ▲ 1 | qwen2-72b-instructOpenAlibaba | 1,264 | ±5 | 38,872 | — |
| 45 | ▲ 1 | gemma-2-9b-itOpenGoogle | 1,263 | ±4 | 57,197 | — |
| 46 | ▼ 2 | deepseek-coder-v2OpenDeepSeek | 1,263 | ±6 | 15,753 | — |
| 47 | — | phi-4OpenMicrosoft | 1,258 | ±5 | 25,213 | — |
| 48 | ▲ 1 | olmo-2-0325-32b-instructOpenAi2 | 1,256 | ±11 | 3,460 | — |
| 49 | ▼ 1 | command-r-08-2024OpenCohere | 1,254 | ±6 | 10,851 | — |
| 50 | — | jamba-1.5-miniOpenAI21 Labs | 1,240 | ±7 | 9,274 | — |
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