Model rankings
1133 models · 5 boards · 2 sources
Smartest
Best open model
Best value
Best from China
Top three by Intelligence
Gemini 3.1 Pro PreviewGoogle57.2
GPT-5.4 (xhigh)OpenAI56.8
GPT-5.3 Codex (xhigh)OpenAI53.6
Top three open models
GLM-5.1 (Reasoning)Z AI · #7 overall51.4
GLM-5 (Reasoning)Z AI · #10 overall49.8
MiniMax-M2.7MiniMax · #12 overall49.6
This week's changes
claude-opus-4-7Coding · #1New
Gemini 3.1 Flash TTSSpeech · #2New
ImagineArt 2.0Image · #11New
AsyncFlow V2, asyncSpeech · #32New
Lightning v3.1Speech · #46New
| Rank | Change | Model | Intelligence | Price $/M | Speed tok/s | First token |
|---|---|---|---|---|---|---|
| 1 | — | Gemma 4 31B (Reasoning)OpenGoogle · 1 more variant | 39.2 | $0.000 | 36 | 1.7 s |
| 2 | — | NVIDIA Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA | 36.0 | $0.41 | 193 | 1.1 s |
| 3 | — | gpt-oss-120B (high)OpenOpenAI · 1 more variant | 33.3 | $0.26 | 206 | 0.9 s |
| 4 | — | Gemma 4 26B A4B (Reasoning)OpenGoogle · 1 more variant | 31.2 | $0.20 | — | — |
| 5 | — | Nemotron Cascade 2 30B A3BOpenNVIDIA | 28.4 | — | — | — |
| 6 | — | gpt-oss-20B (high)OpenOpenAI · 1 more variant | 24.5 | $0.10 | 265 | 0.7 s |
| 7 | — | NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA · 1 more variant | 24.3 | $0.11 | 171 | 2.5 s |
| 8 | — | Gemma 4 E4B (Reasoning)OpenGoogle · 1 more variant | 18.8 | — | — | — |
| 9 | — | Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant | 18.7 | $0.18 | 59 | 1.5 s |
| 10 | — | Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant | 18.5 | — | — | — |
| 11 | — | Llama 4 MaverickOpenMeta | 18.4 | $0.48 | 106 | 1.1 s |
| 12 | — | Llama 3.1 Instruct 405BOpenMeta | 17.4 | $3.7 | 29 | 2.6 s |
| 13 | — | Gemma 4 E2B (Reasoning)OpenGoogle · 1 more variant | 15.2 | — | — | — |
| 14 | — | Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA | 15.0 | $0.90 | 42 | 2.5 s |
| 15 | — | NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA · 1 more variant | 14.9 | $0.30 | 133 | 0.9 s |
| 16 | — | NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA · 1 more variant | 14.8 | $0.070 | 132 | 0.7 s |
| 17 | — | NVIDIA Nemotron 3 Nano 4BOpenNVIDIA | 14.7 | — | — | — |
| 18 | — | Llama 3.3 Instruct 70BOpenMeta | 14.5 | $0.62 | 87 | 1.4 s |
| 19 | — | Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA | 14.4 | — | — | — |
| 20 | — | Grok 2 (Dec '24)OpenxAI | 13.9 | — | — | — |
| 21 | — | Llama 4 ScoutOpenMeta | 13.5 | $0.29 | 127 | 0.8 s |
| 22 | — | Llama 3.1 Nemotron Instruct 70BOpenNVIDIA | 13.4 | $1.2 | 37 | 1.9 s |
| 23 | — | Llama 3.1 Instruct 70BOpenMeta | 12.5 | $0.56 | 20 | 2.1 s |
| 24 | — | R1 1776OpenPerplexity | 12.0 | — | — | — |
| 25 | — | Llama 3.2 Instruct 90B (Vision)OpenMeta | 11.9 | $0.72 | 50 | 1.0 s |
| 26 | — | Llama 3.1 Instruct 8BOpenMeta | 11.8 | $0.10 | 143 | 0.9 s |
| 27 | — | Grok-1OpenxAI | 11.7 | — | — | — |
| 28 | — | Granite 4.0 H SmallOpenIBM | 10.8 | $0.11 | 358 | 10 s |
| 29 | — | LFM2 24B A2BOpenLiquid AI | 10.5 | $0.053 | 93 | 0.5 s |
| 30 | — | Phi-4OpenMicrosoft Azure | 10.4 | $0.22 | 25 | 2.3 s |
| 31 | — | Gemma 3 27B InstructOpenGoogle | 10.3 | $0.000 | 26 | 2.1 s |
| 32 | — | Phi-3 Mini Instruct 3.8BOpenMicrosoft Azure | 10.1 | — | — | — |
| 33 | — | Gemma 3n E4B Instruct Preview (May '25)OpenGoogle | 10.1 | — | — | — |
| 34 | — | Phi-4 Multimodal InstructOpenMicrosoft Azure | 10.0 | $0.000 | 16 | 0.8 s |
| 35 | — | Llama 2 Chat 7BOpenMeta | 9.7 | $0.10 | — | — |
| 36 | — | Llama 3.2 Instruct 3BOpenMeta | 9.7 | $0.085 | 53 | 1.0 s |
| 37 | — | Llama 3 Instruct 70BOpenMeta | 8.9 | $0.87 | — | — |
| 38 | — | Arctic InstructOpenSnowflake | 8.8 | — | — | — |
| 39 | — | Gemma 3 12B InstructOpenGoogle | 8.8 | $0.000 | 27 | 30 s |
| 40 | — | Llama 3.2 Instruct 11B (Vision)OpenMeta | 8.7 | $0.25 | 50 | 0.7 s |
| 41 | — | Phi-4 Mini InstructOpenMicrosoft Azure | 8.4 | $0.000 | 42 | 0.9 s |
| 42 | — | Llama 2 Chat 70BOpenMeta | 8.4 | — | — | — |
| 43 | — | Llama 2 Chat 13BOpenMeta | 8.4 | — | — | — |
| 44 | — | DBRX InstructOpenDatabricks | 8.3 | — | — | — |
| 45 | — | LFM2.5-1.2B-ThinkingOpenLiquid AI | 8.1 | — | — | — |
| 46 | — | LFM2 2.6BOpenLiquid AI | 8.0 | $0.000 | — | — |
| 46 | — | LFM2.5-1.2B-InstructOpenLiquid AI | 8.0 | $0.000 | — | — |
| 48 | — | Granite 4.0 H 1BOpenIBM | 8.0 | — | — | — |
| 49 | — | Gemma 3 270MOpenGoogle | 7.7 | — | — | — |
| 50 | — | Granite 4.0 MicroOpenIBM | 7.7 | — | — | — |
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