Model rankings
481 models · 3 boards · 2 sources
Smartest
Best open model
Best value
Best from China
Top three open models
Qwen3 235B A22B 2507 (Reasoning)Alibaba · #6 overall68.9
DeepSeek R1 0528 (May '25)DeepSeek · #8 overall68.3
GLM-4.5Z AI · #10 overall65.7
This week's changes
GLM-4.5Intelligence · #10New
EXAONE 4.0 32B (Reasoning)Intelligence · #14New
Llama Nemotron Super 49B v1.5 (Reasoning)Intelligence · #16New
Sonar Reasoning ProIntelligence · #21New
GLM-4.5-AirIntelligence · #24New
| Rank | Change | Model | Intelligence | Price $/M | Speed tok/s | First token |
|---|---|---|---|---|---|---|
| 1 | New | Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant | 63.8 | $0.000 | — | — |
| 2 | ▼ 1 | Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA | 60.8 | $0.90 | — | — |
| 3 | ▲ 10 | R1 1776OpenPerplexity | 53.7 | $3.5 | — | — |
| 4 | ▼ 2 | Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant | 51.2 | $0.000 | — | — |
| 5 | ▼ 2 | Llama 4 MaverickOpenMeta | 50.5 | $0.39 | — | — |
| 6 | ▼ 2 | Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA | 45.0 | $0.000 | — | — |
| 7 | ▼ 2 | Llama 4 ScoutOpenMeta | 43.0 | $0.23 | — | — |
| 8 | ▼ 2 | Llama 3.3 Instruct 70BOpenMeta | 41.1 | $0.60 | — | — |
| 9 | ▼ 2 | Llama 3.1 Instruct 405BOpenMeta | 40.5 | $3.3 | — | — |
| 10 | ▼ 2 | Phi-4OpenMicrosoft Azure | 40.2 | $0.22 | — | — |
| 11 | ▼ 2 | Gemma 3 27B InstructOpenGoogle | 37.6 | $0.000 | — | — |
| 12 | ▼ 2 | Llama 3.1 Nemotron Instruct 70BOpenNVIDIA | 37.3 | $0.16 | — | — |
| 13 | ▼ 2 | Llama 3.1 Instruct 70BOpenMeta | 35.4 | $0.76 | — | — |
| 14 | ▼ 2 | Gemma 3 12B InstructOpenGoogle | 33.8 | $0.063 | — | — |
| 15 | ▼ 1 | Llama 3.2 Instruct 90B (Vision)OpenMeta | 33.4 | $0.54 | — | — |
| 16 | ▼ 1 | Grok-1OpenxAI | 32.7 | $0.000 | — | — |
| 17 | ▼ 1 | Gemma 2 27BOpenGoogle | 31.7 | $0.80 | — | — |
| 18 | ▼ 1 | Gemma 3n E4B InstructOpenGoogle | 28.0 | $0.025 | — | — |
| 19 | ▼ 1 | Llama 3 Instruct 70BOpenMeta | 27.5 | $0.75 | — | — |
| 20 | ▼ 1 | Gemma 3n E4B Instruct Preview (May '25)OpenGoogle | 27.0 | $0.000 | — | — |
| 21 | ▼ 1 | Phi-4 Multimodal InstructOpenMicrosoft Azure | 26.9 | $0.000 | — | — |
| 22 | ▼ 1 | Phi-4 Mini InstructOpenMicrosoft Azure | 26.0 | $0.000 | — | — |
| 23 | ▼ 1 | Granite 3.3 Instruct 8BOpenIBM | 25.9 | $0.000 | — | — |
| 24 | ▼ 1 | Gemma 3 4B InstructOpenGoogle | 25.4 | $0.025 | — | — |
| 25 | — | Phi-3 Medium Instruct 14BOpenMicrosoft Azure | 24.5 | $0.30 | — | — |
| 26 | — | Llama 3.1 Instruct 8BOpenMeta | 23.7 | $0.10 | — | — |
| 27 | ▼ 3 | Llama 3.2 Instruct 11B (Vision)OpenMeta | 23.2 | $0.10 | — | — |
| 28 | ▼ 1 | Gemma 3n E2B InstructOpenGoogle | 22.4 | $0.000 | — | — |
| 29 | ▼ 1 | Gemma 2 9BOpenGoogle | 22.2 | $0.20 | — | — |
| 30 | ▼ 1 | Phi-3 Mini Instruct 3.8BOpenMicrosoft Azure | 22.1 | $0.000 | — | — |
| 31 | ▼ 1 | Arctic InstructOpenSnowflake | 22.0 | $0.000 | — | — |
| 32 | ▼ 1 | Llama 3 Instruct 8BOpenMeta | 21.5 | $0.058 | — | — |
| 33 | ▼ 1 | Llama 2 Chat 70BOpenMeta | 20.0 | $0.000 | — | — |
| 34 | ▼ 1 | Llama 2 Chat 13BOpenMeta | 19.9 | $0.000 | — | — |
| 35 | ▼ 1 | DBRX InstructOpenDatabricks | 19.8 | $0.000 | — | — |
| 36 | ▼ 1 | Llama 3.2 Instruct 3BOpenMeta | 19.5 | $0.035 | — | — |
| 37 | ▼ 1 | Gemma 3 1B InstructOpenGoogle | 13.4 | $0.000 | — | — |
| 38 | ▼ 1 | Llama 65BOpenMeta | 11.0 | $0.000 | — | — |
| 39 | ▼ 1 | Llama 3.2 Instruct 1BOpenMeta | 9.7 | $0.053 | — | — |
| 40 | ▼ 1 | Llama 2 Chat 7BOpenMeta | 8.3 | $0.10 | — | — |
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