Model rankings
656 models · 3 boards · 2 sources
Smartest
Best open model
Best value
Best from China
Top three open models
gpt-oss-120B (high)OpenAI · #12 overall58.0
DeepSeek V3.1 Terminus (Reasoning)DeepSeek · #13 overall57.7
Qwen3 235B A22B 2507 (Reasoning)Alibaba · #14 overall57.5
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 | Intelligence | Price $/M | Speed tok/s | First token |
|---|---|---|---|---|---|---|
| 1 | — | gpt-oss-120B (high)OpenOpenAI | 58.0 | $0.26 | — | — |
| 2 | New | Apriel-v1.5-15B-ThinkerOpenServiceNow | 51.6 | $0.000 | — | — |
| 3 | ▼ 1 | Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant | 45.2 | $0.18 | — | — |
| 4 | ▼ 1 | gpt-oss-20B (high)OpenOpenAI | 43.3 | $0.095 | — | — |
| 5 | ▼ 1 | Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA | 38.5 | $0.90 | — | — |
| 6 | ▼ 1 | NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA · 1 more variant | 36.9 | $0.070 | — | — |
| 7 | ▼ 1 | Llama 4 MaverickOpenMeta | 35.8 | $0.39 | — | — |
| 8 | ▼ 1 | Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant | 35.5 | $0.000 | — | — |
| 9 | ▼ 1 | Llama 4 ScoutOpenMeta | 28.1 | $0.26 | — | — |
| 10 | ▼ 1 | Llama 3.3 Instruct 70BOpenMeta | 27.9 | $0.57 | — | — |
| 11 | ▼ 1 | Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA | 26.1 | $0.000 | — | — |
| 12 | ▼ 1 | Llama 3.1 Instruct 405BOpenMeta | 25.7 | $3.1 | — | — |
| 13 | ▼ 1 | Grok 2 (Dec '24)OpenxAI | 24.7 | $0.000 | — | — |
| 14 | ▼ 1 | Phi-4OpenMicrosoft Azure | 24.6 | $0.22 | — | — |
| 15 | ▼ 1 | Llama 3.1 Nemotron Instruct 70BOpenNVIDIA | 23.6 | $0.60 | — | — |
| 16 | New | Granite 4.0 H SmallOpenIBM | 22.7 | $0.11 | — | — |
| 17 | ▼ 2 | Llama 3.1 Instruct 70BOpenMeta | 22.6 | $0.76 | — | — |
| 18 | ▼ 2 | Gemma 3 27B InstructOpenGoogle | 21.6 | $0.000 | — | — |
| 19 | ▼ 2 | Gemma 3 12B InstructOpenGoogle | 20.4 | $0.000 | — | — |
| 20 | ▼ 2 | R1 1776OpenPerplexity | 19.1 | $3.5 | — | — |
| 21 | ▼ 2 | Llama 3.2 Instruct 90B (Vision)OpenMeta | 18.9 | $0.72 | — | — |
| 22 | ▼ 2 | Grok-1OpenxAI | 18.2 | $0.000 | — | — |
| 23 | ▼ 2 | Gemma 2 27BOpenGoogle | 17.2 | $0.000 | — | — |
| 24 | ▼ 2 | Llama 3.1 Instruct 8BOpenMeta | 16.9 | $0.10 | — | — |
| 25 | New | Granite 4.0 MicroOpenIBM | 16.2 | $0.000 | — | — |
| 26 | ▼ 3 | Phi-4 Mini InstructOpenMicrosoft Azure | 15.7 | $0.000 | — | — |
| 27 | ▼ 3 | Llama 3.2 Instruct 11B (Vision)OpenMeta | 15.5 | $0.16 | — | — |
| 28 | ▼ 3 | Gemma 3n E4B InstructOpenGoogle | 15.5 | $0.025 | — | — |
| 29 | ▼ 3 | Granite 3.3 8B (Non-reasoning)OpenIBM | 15.2 | $0.085 | — | — |
| 30 | ▼ 3 | Gemma 3 4B InstructOpenGoogle | 14.7 | $0.000 | — | — |
| 31 | ▼ 3 | Phi-3 Mini Instruct 3.8BOpenMicrosoft Azure | 13.1 | $0.23 | — | — |
| 32 | ▼ 3 | Llama 3 Instruct 70BOpenMeta | 13.0 | $0.75 | — | — |
| 33 | ▼ 3 | Gemma 3n E4B Instruct Preview (May '25)OpenGoogle | 12.5 | $0.000 | — | — |
| 34 | ▼ 3 | Phi-4 Multimodal InstructOpenMicrosoft Azure | 12.4 | $0.000 | — | — |
| 35 | ▼ 3 | LFM2 2.6BOpenLiquid AI | 11.8 | $0.000 | — | — |
| 36 | ▼ 3 | Llama 2 Chat 7BOpenMeta | 11.3 | $0.10 | — | — |
| 37 | ▼ 3 | Llama 3.2 Instruct 3BOpenMeta | 11.2 | $0.048 | — | — |
| 38 | ▼ 3 | Phi-3 Medium Instruct 14BOpenMicrosoft Azure | 10.1 | $0.30 | — | — |
| 39 | ▼ 3 | LFM2 1.2BOpenLiquid AI | 8.0 | $0.000 | — | — |
| 40 | ▼ 3 | Gemma 3n E2B InstructOpenGoogle | 8.0 | $0.000 | — | — |
| 41 | ▼ 3 | Gemma 2 9BOpenGoogle | 7.8 | $0.20 | — | — |
| 42 | ▼ 3 | Arctic InstructOpenSnowflake | 7.6 | $0.000 | — | — |
| 43 | ▼ 3 | Llama 3.2 Instruct 1BOpenMeta | 7.1 | $0.053 | — | — |
| 44 | ▼ 3 | Llama 3 Instruct 8BOpenMeta | 7.0 | $0.055 | — | — |
| 45 | ▼ 3 | Gemma 3 1B InstructOpenGoogle | 6.1 | $0.000 | — | — |
| 46 | ▼ 3 | Llama 2 Chat 70BOpenMeta | 5.6 | $0.000 | — | — |
| 47 | ▼ 3 | Llama 2 Chat 13BOpenMeta | 5.5 | $0.000 | — | — |
| 48 | ▼ 3 | DBRX InstructOpenDatabricks | 5.3 | $0.000 | — | — |
| 49 | ▼ 3 | Llama 65BOpenMeta | 1.0 | $0.000 | — | — |
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