Model rankings
1055 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)OpenAI57.0
GPT-5.3 Codex (xhigh)OpenAI54.0
Top three open models
GLM-5 (Reasoning)Z AI · #7 overall49.8
Kimi K2.5 (Reasoning)Kimi · #12 overall46.8
Qwen3.5 397B A17B (Reasoning)Alibaba · #14 overall45.1
This week's changes
GPT-5.4 (xhigh)Intelligence · #2New
gpt-5.4-high (codex-harness)Coding · #5New
gpt-5.4-medium (codex-harness)Coding · #12New
Step 3.5 FlashIntelligence · #35New
Gemini 3.1 Flash-Lite PreviewIntelligence · #46New
| 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 | — | Apriel-v1.5-15B-ThinkerOpenServiceNow | 28.3 | $0.000 | — | — |
| 3 | — | Apriel-v1.6-15B-ThinkerOpenServiceNow | 27.6 | $0.000 | — | — |
| 4 | — | gpt-oss-20B (high)OpenOpenAI · 1 more variant | 24.5 | $0.095 | — | — |
| 5 | — | NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA · 1 more variant | 24.3 | $0.11 | — | — |
| 6 | ▲ 1 | NVIDIA Nemotron Nano 9B V2 (Non-reasoning)OpenNVIDIA · 1 more variant | 18.8 | $0.10 | — | — |
| 7 | ▲ 1 | Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant | 18.7 | $0.18 | — | — |
| 8 | ▲ 1 | Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant | 18.5 | $0.000 | — | — |
| 9 | ▲ 1 | Llama 4 MaverickOpenMeta | 18.4 | $0.44 | — | — |
| 10 | ▲ 1 | Llama 3.1 Instruct 405BOpenMeta | 17.4 | $5.4 | — | — |
| 11 | ▲ 1 | Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA | 15.0 | $0.90 | — | — |
| 12 | ▼ 6 | NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA · 1 more variant | 14.9 | $0.30 | — | — |
| 13 | — | Llama 3.3 Instruct 70BOpenMeta | 14.5 | $0.62 | — | — |
| 14 | — | Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA | 14.4 | $0.000 | — | — |
| 15 | — | Grok 2 (Dec '24)OpenxAI | 13.9 | $0.000 | — | — |
| 16 | — | Llama 4 ScoutOpenMeta | 13.5 | $0.30 | — | — |
| 17 | — | Llama 3.1 Nemotron Instruct 70BOpenNVIDIA | 13.4 | $1.2 | — | — |
| 18 | ▲ 2 | Llama 3.1 Instruct 70BOpenMeta | 12.5 | $0.56 | — | — |
| 19 | ▲ 3 | R1 1776OpenPerplexity | 12.0 | $0.000 | — | — |
| 20 | ▲ 3 | Llama 3.2 Instruct 90B (Vision)OpenMeta | 11.9 | $0.72 | — | — |
| 21 | ▲ 3 | Llama 3.1 Instruct 8BOpenMeta | 11.8 | $0.10 | — | — |
| 22 | ▲ 3 | Phi-4 Mini InstructOpenMicrosoft Azure | 10.9 | $0.000 | — | — |
| 23 | ▼ 5 | Granite 4.0 H SmallOpenIBM | 10.8 | $0.11 | — | — |
| 24 | ▲ 3 | LFM2 24B A2BOpenLiquid AI | 10.5 | $0.053 | — | — |
| 25 | ▼ 6 | Phi-4OpenMicrosoft Azure | 10.4 | $0.22 | — | — |
| 26 | ▲ 3 | Gemma 3 27B InstructOpenGoogle | 10.3 | $0.000 | — | — |
| 27 | ▲ 3 | Gemma 3n E4B Instruct Preview (May '25)OpenGoogle | 10.1 | $0.000 | — | — |
| 28 | ▲ 3 | Phi-4 Multimodal InstructOpenMicrosoft Azure | 10.0 | $0.000 | — | — |
| 29 | ▲ 3 | Llama 3.2 Instruct 3BOpenMeta | 9.7 | $0.080 | — | — |
| 30 | ▼ 9 | Gemma 3 12B InstructOpenGoogle | 8.8 | $0.000 | — | — |
| 31 | ▼ 5 | Llama 3.2 Instruct 11B (Vision)OpenMeta | 8.7 | $0.16 | — | — |
| 32 | ▲ 2 | DBRX InstructOpenDatabricks | 8.3 | $0.000 | — | — |
| 33 | ▲ 2 | LFM2.5-1.2B-ThinkingOpenLiquid AI | 8.1 | $0.000 | — | — |
| 34 | ▲ 2 | LFM2 2.6BOpenLiquid AI | 8.0 | $0.000 | — | — |
| 34 | New | LFM2.5-1.2B-InstructOpenLiquid AI | 8.0 | $0.000 | — | — |
| 36 | ▼ 8 | Granite 4.0 H 1BOpenIBM | 8.0 | $0.000 | — | — |
| 37 | — | Gemma 3 270MOpenGoogle | 7.7 | $0.000 | — | — |
| 38 | — | Granite 4.0 MicroOpenIBM | 7.7 | $0.000 | — | — |
| 39 | — | Granite 4.0 1BOpenIBM | 7.3 | $0.000 | — | — |
| 40 | — | LFM2 8B A1BOpenLiquid AI | 7.0 | $0.000 | — | — |
| 41 | — | Granite 3.3 8B (Non-reasoning)OpenIBM | 7.0 | $0.085 | — | — |
| 42 | — | Gemma 3n E4B InstructOpenGoogle | 6.4 | $0.025 | — | — |
| 43 | — | LFM2 1.2BOpenLiquid AI | 6.3 | $0.000 | — | — |
| 44 | — | Gemma 3 4B InstructOpenGoogle | 6.3 | $0.000 | — | — |
| 45 | — | Llama 3.2 Instruct 1BOpenMeta | 6.3 | $0.10 | — | — |
| 46 | — | LFM2.5-VL-1.6BOpenLiquid AI | 6.2 | $0.000 | — | — |
| 47 | ▼ 14 | Granite 4.0 350MOpenIBM | 6.1 | $0.000 | — | — |
| 48 | ▼ 1 | Gemma 3 1B InstructOpenGoogle | 5.6 | $0.000 | — | — |
| 49 | ▼ 1 | Granite 4.0 H 350MOpenIBM | 5.4 | $0.000 | — | — |
| 50 | ▼ 1 | Gemma 3n E2B InstructOpenGoogle | 4.8 | $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