Model rankings
1125 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
Kimi K2.5 (Reasoning)Kimi · #20 overall46.8
This week's changes
HappyHorse-1.0Video · #1New
glm-5.1Coding · #2New
Dreamina Seedance 2.0 720pVideo · #2New
Eleven v3Speech · #2New
Speech 2.8 HDSpeech · #4New
| Rank | Change | Model | Intelligence | Price $/M | Speed tok/s | First token |
|---|---|---|---|---|---|---|
| 1 | New | Gemma 4 31B (Reasoning)OpenGoogle · 1 more variant | 39.2 | $0.000 | 36 | 1.7 s |
| 2 | ▼ 1 | NVIDIA Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA | 36.0 | $0.41 | 172 | 1.0 s |
| 3 | ▼ 1 | gpt-oss-120B (high)OpenOpenAI · 1 more variant | 33.3 | $0.26 | 215 | 0.9 s |
| 4 | New | Gemma 4 26B A4B (Reasoning)OpenGoogle · 1 more variant | 31.2 | $0.20 | — | — |
| 5 | ▼ 2 | Nemotron Cascade 2 30B A3BOpenNVIDIA | 27.7 | — | — | — |
| 6 | ▼ 2 | gpt-oss-20B (high)OpenOpenAI · 1 more variant | 24.5 | $0.095 | 249 | 0.7 s |
| 7 | ▼ 2 | NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA · 1 more variant | 24.3 | $0.11 | 101 | 1.7 s |
| 8 | New | Gemma 4 E4B (Reasoning)OpenGoogle · 1 more variant | 18.8 | — | — | — |
| 9 | ▼ 3 | Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant | 18.7 | $0.18 | 55 | 1.5 s |
| 10 | ▼ 3 | Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant | 18.5 | — | — | — |
| 11 | ▼ 3 | Llama 4 MaverickOpenMeta | 18.4 | $0.46 | 110 | 1.0 s |
| 12 | ▼ 3 | Llama 3.1 Instruct 405BOpenMeta | 17.4 | $3.7 | 29 | 2.4 s |
| 13 | New | Gemma 4 E2B (Reasoning)OpenGoogle · 1 more variant | 15.2 | — | — | — |
| 14 | ▼ 4 | Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA | 15.0 | $0.90 | 41 | 2.5 s |
| 15 | ▼ 4 | NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA · 1 more variant | 14.9 | $0.30 | 142 | 0.6 s |
| 16 | ▼ 4 | NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA · 1 more variant | 14.8 | $0.070 | 157 | 0.6 s |
| 17 | ▼ 4 | NVIDIA Nemotron 3 Nano 4BOpenNVIDIA | 14.7 | — | — | — |
| 18 | ▼ 4 | Llama 3.3 Instruct 70BOpenMeta | 14.5 | $0.61 | 87 | 1.4 s |
| 19 | ▼ 4 | Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA | 14.4 | — | — | — |
| 20 | ▼ 4 | Grok 2 (Dec '24)OpenxAI | 13.9 | — | — | — |
| 21 | ▼ 4 | Llama 4 ScoutOpenMeta | 13.5 | $0.29 | 143 | 0.8 s |
| 22 | ▼ 4 | Llama 3.1 Nemotron Instruct 70BOpenNVIDIA | 13.4 | $1.2 | 46 | 1.9 s |
| 23 | ▼ 4 | Llama 3.1 Instruct 70BOpenMeta | 12.5 | $0.56 | 27 | 2.1 s |
| 24 | ▼ 4 | R1 1776OpenPerplexity | 12.0 | — | — | — |
| 25 | ▼ 4 | Llama 3.2 Instruct 90B (Vision)OpenMeta | 11.9 | $0.72 | 54 | 1.1 s |
| 26 | ▼ 4 | Llama 3.1 Instruct 8BOpenMeta | 11.8 | $0.10 | 150 | 0.8 s |
| 27 | ▼ 4 | Grok-1OpenxAI | 11.7 | — | — | — |
| 28 | ▼ 4 | Granite 4.0 H SmallOpenIBM | 10.8 | $0.11 | 442 | 10 s |
| 29 | ▼ 4 | LFM2 24B A2BOpenLiquid AI | 10.5 | $0.053 | 52 | 0.5 s |
| 30 | ▼ 4 | Phi-4OpenMicrosoft Azure | 10.4 | $0.22 | 34 | 2.1 s |
| 31 | ▼ 4 | Gemma 3 27B InstructOpenGoogle | 10.3 | $0.000 | 28 | 2.7 s |
| 32 | ▼ 4 | Phi-3 Mini Instruct 3.8BOpenMicrosoft Azure | 10.1 | — | — | — |
| 33 | ▼ 4 | Gemma 3n E4B Instruct Preview (May '25)OpenGoogle | 10.1 | — | — | — |
| 34 | ▼ 4 | Phi-4 Multimodal InstructOpenMicrosoft Azure | 10.0 | $0.000 | 17 | 0.8 s |
| 35 | ▼ 4 | Llama 2 Chat 7BOpenMeta | 9.7 | $0.10 | — | — |
| 36 | ▼ 4 | Llama 3.2 Instruct 3BOpenMeta | 9.7 | $0.085 | 51 | 0.9 s |
| 37 | ▼ 4 | Llama 3 Instruct 70BOpenMeta | 8.9 | $0.87 | — | — |
| 38 | ▼ 4 | Arctic InstructOpenSnowflake | 8.8 | — | — | — |
| 39 | ▼ 4 | Gemma 3 12B InstructOpenGoogle | 8.8 | $0.000 | 29 | 35 s |
| 40 | ▼ 4 | Llama 3.2 Instruct 11B (Vision)OpenMeta | 8.7 | $0.16 | 52 | 0.8 s |
| 41 | ▼ 4 | Phi-4 Mini InstructOpenMicrosoft Azure | 8.4 | $0.000 | 43 | 0.8 s |
| 42 | ▼ 4 | Llama 2 Chat 70BOpenMeta | 8.4 | — | — | — |
| 43 | ▼ 4 | Llama 2 Chat 13BOpenMeta | 8.4 | — | — | — |
| 44 | ▼ 4 | DBRX InstructOpenDatabricks | 8.3 | — | — | — |
| 45 | ▼ 4 | LFM2.5-1.2B-ThinkingOpenLiquid AI | 8.1 | — | — | — |
| 46 | ▼ 4 | LFM2 2.6BOpenLiquid AI | 8.0 | $0.000 | — | — |
| 46 | ▼ 4 | LFM2.5-1.2B-InstructOpenLiquid AI | 8.0 | $0.000 | — | — |
| 48 | ▼ 4 | Granite 4.0 H 1BOpenIBM | 8.0 | — | — | — |
| 49 | ▼ 4 | Gemma 3 270MOpenGoogle | 7.7 | — | — | — |
| 50 | ▼ 4 | 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