Model rankings
984 models · 5 boards · 2 sources
Smartest
Best open model
Best value
Best from China
Top three by Intelligence
GPT-5.2 (xhigh)OpenAI51.2
Claude Opus 4.5 (Reasoning)Anthropic49.7
GPT-5.2 Codex (xhigh)OpenAI49.0
Top three open models
GLM-4.7 (Reasoning)Z AI · #11 overall42.1
DeepSeek V3.2 (Reasoning)DeepSeek · #12 overall41.6
Kimi K2 ThinkingKimi · #16 overall40.7
This week's changes
grok-imagine-videoVideo · #1New
Inworld TTS 1.5 MaxSpeech · #1New
GPT-5.2 Codex (xhigh)Intelligence · #3New
kimi-k2.5-thinkingCoding · #4New
Kling O1 Standard (December)Video · #10New
| Rank | Change | Model | Intelligence | Price $/M | Speed tok/s | First token |
|---|---|---|---|---|---|---|
| 1 | — | gpt-oss-120B (high)OpenOpenAI · 1 more variant | 33.3 | $0.26 | — | — |
| 2 | New | Apriel-v1.5-15B-ThinkerOpenServiceNow | 28.3 | $0.000 | — | — |
| 3 | ▼ 1 | Apriel-v1.6-15B-ThinkerOpenServiceNow | 27.5 | $0.000 | — | — |
| 4 | — | gpt-oss-20B (high)OpenOpenAI · 1 more variant | 24.5 | $0.10 | — | — |
| 5 | ▼ 2 | NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA · 1 more variant | 24.3 | $0.11 | — | — |
| 6 | New | Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA | 20.0 | $0.90 | — | — |
| 7 | ▼ 2 | Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant | 18.6 | $0.18 | — | — |
| 8 | New | Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant | 18.5 | $0.000 | — | — |
| 9 | ▼ 3 | Llama 4 MaverickOpenMeta | 18.3 | $0.44 | — | — |
| 10 | ▼ 1 | NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA · 1 more variant | 14.8 | $0.30 | — | — |
| 11 | ▼ 3 | NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA · 1 more variant | 14.8 | $0.070 | — | — |
| 12 | New | Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA | 14.4 | $0.000 | — | — |
| 13 | ▼ 3 | Llama 3.3 Instruct 70BOpenMeta | 14.2 | $0.62 | — | — |
| 14 | ▼ 7 | Llama 3.1 Instruct 405BOpenMeta | 14.2 | $4.5 | — | — |
| 15 | New | Grok 2 (Dec '24)OpenxAI | 13.9 | $0.000 | — | — |
| 16 | ▼ 5 | Llama 4 ScoutOpenMeta | 13.5 | $0.29 | — | — |
| 17 | ▼ 5 | Llama 3.1 Nemotron Instruct 70BOpenNVIDIA | 13.4 | $1.2 | — | — |
| 18 | New | Phi-4OpenMicrosoft Azure | 13.2 | $0.22 | — | — |
| 19 | New | Llama 3.1 Instruct 70BOpenMeta | 13.1 | $0.56 | — | — |
| 20 | New | R1 1776OpenPerplexity | 12.0 | $0.000 | — | — |
| 21 | New | Llama 3.2 Instruct 90B (Vision)OpenMeta | 11.9 | $0.72 | — | — |
| 22 | New | Grok-1OpenxAI | 11.7 | $0.000 | — | — |
| 23 | ▼ 10 | Llama 3.1 Instruct 8BOpenMeta | 11.7 | $0.10 | — | — |
| 24 | New | Phi-4 Mini InstructOpenMicrosoft Azure | 10.9 | $0.000 | — | — |
| 25 | New | Llama 3.2 Instruct 11B (Vision)OpenMeta | 10.9 | $0.16 | — | — |
| 26 | ▼ 12 | Granite 4.0 H SmallOpenIBM | 10.8 | $0.11 | — | — |
| 27 | New | Granite 3.3 8B (Non-reasoning)OpenIBM | 10.8 | $0.085 | — | — |
| 28 | New | Llama 3 Instruct 70BOpenMeta | 10.2 | $0.57 | — | — |
| 29 | ▼ 14 | Gemma 3 27B InstructOpenGoogle | 10.2 | $0.000 | — | — |
| 30 | New | Phi-3 Mini Instruct 3.8BOpenMicrosoft Azure | 10.1 | $0.23 | — | — |
| 31 | New | Gemma 3n E4B Instruct Preview (May '25)OpenGoogle | 10.1 | $0.000 | — | — |
| 32 | New | Phi-4 Multimodal InstructOpenMicrosoft Azure | 10.0 | $0.000 | — | — |
| 33 | New | Llama 2 Chat 7BOpenMeta | 9.7 | $0.10 | — | — |
| 34 | New | Gemma 3n E2B InstructOpenGoogle | 9.7 | $0.000 | — | — |
| 35 | New | Llama 3.2 Instruct 3BOpenMeta | 9.7 | $0.060 | — | — |
| 36 | New | Llama 3.2 Instruct 1BOpenMeta | 9.1 | $0.053 | — | — |
| 37 | New | Arctic InstructOpenSnowflake | 8.8 | $0.000 | — | — |
| 38 | ▼ 22 | Gemma 3 12B InstructOpenGoogle | 8.8 | $0.000 | — | — |
| 39 | New | Llama 3 Instruct 8BOpenMeta | 8.7 | $0.073 | — | — |
| 40 | New | Gemma 3 1B InstructOpenGoogle | 8.6 | $0.000 | — | — |
| 41 | New | Gemma 3 270MOpenGoogle | 8.4 | $0.000 | — | — |
| 42 | New | Llama 2 Chat 70BOpenMeta | 8.4 | $0.000 | — | — |
| 43 | New | Llama 2 Chat 13BOpenMeta | 8.4 | $0.000 | — | — |
| 44 | New | DBRX InstructOpenDatabricks | 8.3 | $0.000 | — | — |
| 45 | New | LFM2.5-1.2B-ThinkingOpenLiquid AI | 8.1 | $0.000 | — | — |
| 46 | ▼ 29 | Granite 4.0 H 1BOpenIBM | 8.0 | $0.000 | — | — |
| 47 | New | LFM2.5-1.2B-InstructOpenLiquid AI | 8.0 | $0.000 | — | — |
| 48 | ▼ 30 | LFM2 2.6BOpenLiquid AI | 7.9 | $0.000 | — | — |
| 49 | New | Granite 4.0 MicroOpenIBM | 7.7 | $0.000 | — | — |
| 50 | New | Llama 65BOpenMeta | 7.4 | $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