Model rankings
656 models · 3 boards · 2 sources
Most preferred
Best open model
Best from China
Most voted
Top three by Score
gemini-2.5-proGoogle1,452
claude-sonnet-4-5-20250929-thinking-32kAnthropic1,448
claude-opus-4-1-20250805-thinking-16kAnthropic1,448
Top three open models
glm-4.6Z.ai · #13 overall1,421
qwen3-235b-a22b-instruct-2507Alibaba · #16 overall1,419
deepseek-v3.2-exp-thinkingDeepSeek · #17 overall1,418
This week's changes
DeepSeek V3.2 Exp (Reasoning)Intelligence · #16New
GLM-4.6 (Reasoning)Intelligence · #18New
Apriel-v1.5-15B-ThinkerIntelligence · #27New
Qwen3 4B 2507 InstructIntelligence · #88New
Granite 4.0 H SmallIntelligence · #122New
| Rank | Change | Model | Score | 95% interval | Votes | Price $/M |
|---|---|---|---|---|---|---|
| 1 | — | glm-4.6OpenZ.ai | 1,421 | ±11 | 2,935 | — |
| 2 | — | qwen3-235b-a22b-instruct-2507OpenAlibaba | 1,419 | ±5 | 27,832 | — |
| 3 | — | deepseek-v3.2-exp-thinkingOpenDeepSeek · 1 more variant | 1,418 | ±11 | 2,861 | — |
| 4 | — | qwen3-vl-235b-a22b-instructOpenAlibaba | 1,418 | ±9 | 4,794 | — |
| 5 | — | deepseek-r1-0528OpenDeepSeek · 1 more variant | 1,417 | ±6 | 19,488 | — |
| 6 | — | kimi-k2-0905-previewOpenMoonshot AI · 1 more variant | 1,416 | ±7 | 10,933 | — |
| 7 | — | deepseek-v3.1-thinkingOpenDeepSeek · 1 more variant | 1,415 | ±7 | 12,288 | — |
| 8 | — | deepseek-v3.1-terminusOpenDeepSeek · 1 more variant | 1,415 | ±10 | 3,840 | — |
| 9 | — | glm-4.5OpenZ.ai | 1,407 | ±5 | 21,427 | — |
| 10 | — | qwen3-next-80b-a3b-instructOpenAlibaba | 1,403 | ±7 | 11,173 | — |
| 11 | — | longcat-flash-chatOpenMeituan | 1,400 | ±7 | 10,584 | — |
| 12 | — | qwen3-235b-a22b-no-thinkingOpenAlibaba | 1,397 | ±5 | 38,800 | — |
| 13 | — | qwen3-235b-a22b-thinking-2507OpenAlibaba | 1,397 | ±6 | 9,483 | — |
| 14 | — | deepseek-v3-0324OpenDeepSeek · 1 more variant | 1,391 | ±4 | 43,142 | — |
| 15 | — | qwen3-vl-235b-a22b-thinkingOpenAlibaba | 1,387 | ±9 | 4,504 | — |
| 16 | — | qwen3-30b-a3b-instruct-2507OpenAlibaba | 1,385 | ±5 | 20,396 | — |
| 17 | — | qwen3-coder-480b-a35b-instructOpenAlibaba | 1,382 | ±5 | 22,358 | — |
| 18 | — | qwen3-235b-a22bOpenAlibaba | 1,372 | ±5 | 26,355 | — |
| 19 | — | qwen3-next-80b-a3b-thinkingOpenAlibaba | 1,370 | ±7 | 10,017 | — |
| 20 | — | glm-4.5-airOpenZ.ai | 1,369 | ±5 | 20,529 | — |
| 21 | — | minimax-m1OpenMiniMax | 1,367 | ±5 | 30,720 | — |
| 22 | — | gemma-3-27b-itOpenGoogle | 1,362 | ±4 | 43,231 | — |
| 23 | — | mistral-small-2506OpenMistral | 1,351 | ±5 | 17,506 | — |
| 24 | ▲ 2 | command-a-03-2025OpenCohere | 1,348 | ±4 | 46,096 | — |
| 25 | New | ling-flash-2.0OpenAnt Group | 1,348 | ±10 | 3,374 | — |
| 26 | ▼ 2 | glm-4.5vOpenZ.ai | 1,347 | ±9 | 3,925 | — |
| 27 | ▼ 2 | gpt-oss-120bOpenOpenAI | 1,346 | ±6 | 19,656 | $0.26 |
| 28 | ▼ 1 | llama-3.1-nemotron-ultra-253b-v1OpenNVIDIA | 1,344 | ±12 | 2,573 | — |
| 29 | — | qwen3-32bOpenAlibaba | 1,343 | ±10 | 3,943 | — |
| 30 | ▼ 2 | step-3OpenStepFun | 1,343 | ±8 | 5,724 | — |
| 31 | ▼ 1 | gemma-3-12b-itOpenGoogle | 1,340 | ±10 | 3,866 | — |
| 32 | ▼ 1 | nvidia-llama-3.3-nemotron-super-49b-v1.5OpenNVIDIA | 1,339 | ±10 | 3,548 | — |
| 33 | ▼ 1 | llama-3.1-405b-instruct-bf16OpenMeta | 1,334 | ±4 | 41,932 | — |
| 34 | — | llama-3.1-405b-instruct-fp8OpenMeta | 1,333 | ±3 | 60,272 | — |
| 35 | ▼ 2 | qwq-32bOpenAlibaba · 1 more variant | 1,331 | ±4 | 25,707 | — |
| 36 | ▼ 1 | llama-4-maverick-17b-128e-instructOpenMeta | 1,326 | ±4 | 40,473 | — |
| 37 | ▼ 1 | qwen3-30b-a3bOpenAlibaba | 1,324 | ±5 | 26,618 | — |
| 38 | ▼ 1 | llama-3.3-nemotron-49b-super-v1OpenNVIDIA | 1,323 | ±12 | 2,243 | — |
| 39 | ▼ 1 | llama-4-scout-17b-16e-instructOpenMeta | 1,321 | ±5 | 30,487 | — |
| 40 | ▼ 1 | deepseek-v2.5-1210OpenDeepSeek · 1 more variant | 1,320 | ±8 | 6,877 | — |
| 41 | New | ring-flash-2.0OpenAnt Group | 1,318 | ±10 | 3,418 | — |
| 42 | ▼ 2 | gpt-oss-20bOpenOpenAI | 1,318 | ±7 | 9,930 | — |
| 43 | ▼ 1 | gemma-3n-e4b-itOpenGoogle | 1,318 | ±5 | 23,757 | — |
| 44 | ▼ 3 | llama-3.3-70b-instructOpenMeta | 1,317 | ±3 | 54,924 | — |
| 45 | ▼ 2 | qwen-max-0919OpenAlibaba | 1,316 | ±6 | 16,598 | — |
| 46 | ▼ 2 | mistral-large-2407OpenMistral · 1 more variant | 1,312 | ±4 | 45,968 | — |
| 47 | ▼ 2 | athene-v2-chatOpenNexusFlow | 1,311 | ±4 | 24,880 | — |
| 48 | ▼ 2 | athene-70b-0725OpenNexusFlow | 1,304 | ±6 | 19,796 | — |
| 49 | ▼ 2 | gemma-3-4b-itOpenGoogle | 1,302 | ±9 | 4,195 | — |
| 50 | ▼ 2 | qwen2.5-72b-instructOpenAlibaba | 1,300 | ±4 | 39,632 | — |
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