Model rankings
1432 models · 5 boards · 2 sources
Smartest
Best open model
Best value
Best from China
Top three by Intelligence
Claude Opus 5 (Adaptive Reasoning, Max Effort)Anthropic63.1
GPT-5.6 Sol (max)OpenAI60.9
Top three open models
Kimi K3 (max)Kimi · #5 overall59.7
Qwen3.8 2.4T A95BAlibaba · #7 overall57.7
DeepSeek V4 Pro 0813 (Reasoning, Max Effort)DeepSeek · #17 overall53.2
This week's changes
Sonic 3.6Speech · #1New
Grok 4.6 (high)Intelligence · #4New
Qwen3.8 2.4T A95BIntelligence · #7New
glm-5.3-maxCoding · #8New
Qwen-Image-3.0-ProImage · #8New
| Rank | Change | Model | Intelligence | Price $/M | Speed tok/s | First token |
|---|---|---|---|---|---|---|
| 1 | — | Inkling (xhigh)OpenThinking Machines | 42.3 | $1.8 | 84 | 1.7 s |
| 2 | — | Inkling SmallOpenThinking Machines | 41.2 | $0.52 | 64 | 1.8 s |
| 3 | — | Nemotron 3 Ultra 550B A55B (Reasoning)OpenNVIDIA | 38.3 | $1.1 | 140 | 1.8 s |
| 4 | New | Muse Glimmer (high)OpenMeta | 35.1 | $0.58 | 111 | 0.9 s |
| 5 | ▼ 1 | Gemma 4 31B (Reasoning)OpenGoogle · 1 more variant | 29.7 | $0.000 | 36 | 1.1 s |
| 6 | ▼ 1 | Gemma 4 26B A4B (Reasoning)OpenGoogle · 1 more variant | 26.1 | $0.20 | — | — |
| 7 | ▼ 1 | Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA | 25.7 | $0.35 | 132 | 1.9 s |
| 8 | ▼ 1 | gpt-oss-120b (high)OpenOpenAI · 1 more variant | 24.1 | $0.26 | 177 | 0.8 s |
| 9 | New | Nemotron 3.5 LightningOpenNVIDIA | 23.6 | $0.088 | 298 | 1.0 s |
| 10 | ▼ 2 | Gemma 4 12B (Reasoning)OpenGoogle · 1 more variant | 22.2 | $0.15 | 110 | 2.3 s |
| 11 | ▼ 2 | Apriel-v1.5-15B-ThinkerOpenServiceNow | 21.6 | $0.000 | — | — |
| 12 | ▼ 2 | Apriel-v1.6-15B-ThinkerOpenServiceNow | 20.8 | $0.000 | — | — |
| 13 | ▼ 2 | Nemotron Cascade 2 30B A3BOpenNVIDIA | 17.8 | — | — | — |
| 14 | ▼ 2 | gpt-oss-20b (high)OpenOpenAI · 1 more variant | 15.2 | $0.093 | 125 | 1.0 s |
| 15 | ▼ 2 | Nemotron 3 Nano Omni 30B A3B ReasoningOpenNVIDIA | 15.0 | $0.13 | 324 | 1.1 s |
| 16 | ▼ 2 | NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA · 1 more variant | 14.5 | $0.088 | 219 | 1.3 s |
| 17 | ▼ 2 | Llama 4 MaverickOpenMeta | 14.5 | $0.42 | 121 | 1.0 s |
| 18 | ▼ 2 | DiffusionGemma 26B A4BOpenGoogle | 13.5 | — | — | — |
| 19 | ▼ 2 | Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant | 12.4 | $0.40 | 115 | 3.8 s |
| 20 | ▼ 1 | Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant | 12.2 | — | — | — |
| 21 | ▼ 3 | Gemma 4 E4B (Reasoning)OpenGoogle · 1 more variant | 12.2 | $0.040 | 50 | 1.0 s |
| 22 | ▼ 2 | Llama 4 ScoutOpenMeta | 10.3 | $0.30 | 136 | 0.8 s |
| 23 | ▼ 2 | Gemma 4 E2B (Reasoning)OpenGoogle · 1 more variant | 9.5 | — | — | — |
| 24 | ▼ 2 | Llama 3.3 Instruct 70BOpenMeta | 9.3 | $0.67 | 90 | 1.6 s |
| 25 | ▼ 1 | Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA | 8.9 | $0.90 | 53 | 2.5 s |
| 26 | — | NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA · 1 more variant | 8.8 | $0.30 | 138 | 3.7 s |
| 27 | ▼ 4 | Granite 4.1 30BOpenIBM | 8.7 | — | — | — |
| 28 | ▼ 1 | NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA · 1 more variant | 8.7 | $0.070 | 175 | 3.8 s |
| 29 | ▼ 4 | NVIDIA Nemotron 3 Nano 4BOpenNVIDIA | 8.6 | — | — | — |
| 30 | ▼ 2 | Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA | 8.4 | — | — | — |
| 31 | ▼ 2 | Llama 3.1 Instruct 405BOpenMeta | 8.3 | — | — | — |
| 32 | ▼ 2 | LFM2.5-8B-A1BOpenLiquid AI | 8.1 | $0.000 | 336 | 2.0 s |
| 33 | ▼ 1 | Llama 3.1 Nemotron Instruct 70BOpenNVIDIA | 7.4 | $1.2 | 126 | 3.5 s |
| 34 | ▼ 3 | Llama 3.1 Instruct 8BOpenMeta | 7.4 | $0.028 | 136 | 0.9 s |
| 35 | ▼ 2 | Gemma 3 27B InstructOpenGoogle | 7.4 | $0.000 | — | — |
| 36 | ▼ 2 | Llama 3.1 Instruct 70BOpenMeta | 6.5 | $0.56 | 56 | 1.4 s |
| 37 | ▼ 2 | Granite 4.1 8BOpenIBM | 6.4 | $0.063 | 112 | 0.8 s |
| 38 | ▼ 1 | R1 1776OpenPerplexity | 6.0 | — | — | — |
| 39 | ▼ 1 | Llama 3.2 Instruct 90B (Vision)OpenMeta | 6.0 | — | — | — |
| 40 | ▼ 4 | Phi-4 Mini InstructOpenMicrosoft | 5.7 | $0.000 | 44 | 0.9 s |
| 41 | ▼ 2 | Gemma 3 12B InstructOpenGoogle | 5.5 | $0.000 | — | — |
| 42 | ▼ 2 | Granite 4.0 H SmallOpenIBM | 4.9 | $0.11 | 22 | 24 s |
| 43 | ▼ 1 | LFM2 24B A2BOpenLiquid AI | 4.6 | — | — | — |
| 44 | ▼ 1 | Phi-4OpenMicrosoft | 4.6 | $0.22 | 25 | 3.1 s |
| 45 | ▼ 4 | Granite 4.1 3BOpenIBM | 4.4 | — | — | — |
| 46 | ▼ 2 | Phi-3 Mini Instruct 3.8BOpenMicrosoft | 4.3 | — | — | — |
| 47 | ▼ 2 | Gemma 3n E4B Instruct Preview (May '25)OpenGoogle | 4.2 | — | — | — |
| 48 | ▼ 2 | Phi-4 Multimodal InstructOpenMicrosoft | 4.2 | $0.000 | 18 | 0.8 s |
| 49 | ▼ 2 | Llama 2 Chat 7BOpenMeta | 3.9 | $0.10 | — | — |
| 50 | ▼ 2 | Llama 3.2 Instruct 3BOpenMeta | 3.9 | — | — | — |
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