Model rankings
1501 models · 5 boards · 2 sources
Smartest
Best open model
Best value
Best from China
Top three by Intelligence
GPT-6 Astra (max)OpenAI52.8
Claude Opus 5 (Adaptive Reasoning, Max Effort)Anthropic50.7
Top three open models
GLM-5.3 (max)Z AI · #7 overall44.9
Kimi K3 (max)Kimi · #9 overall43.8
GLM-5.3-FlashZ AI · #12 overall41.9
This week's changes
GPT Image 2.5 Flare (max)Image · #1New
GPT Image 2.5 Sunburst (max)Image · #2New
DeepSeek V4.1 Flash (Reasoning, Max Effort)Intelligence · #20New
Agnes 3.0 FlashIntelligence · #27New
Ling-3.0-flash-VLIntelligence · #77New
| Rank | Change | Model | Intelligence | Price $/M | Speed tok/s | First token |
|---|---|---|---|---|---|---|
| 1 | — | Inkling SmallOpenThinking Machines | 26.1 | $0.52 | 167 | 2.2 s |
| 2 | — | Inkling (xhigh)OpenThinking Machines | 25.5 | $1.8 | 89 | 2.9 s |
| 3 | — | Nemotron 3 Ultra 550B A55B (Reasoning)OpenNVIDIA | 23.4 | $1.1 | 203 | 2.3 s |
| 4 | — | Muse Glimmer (high)OpenMeta | 18.1 | $0.64 | 89 | 1.1 s |
| 5 | ▲ 1 | Gemma 4 26B A4B (Reasoning)OpenGoogle · 1 more variant | 16.7 | $0.18 | — | — |
| 6 | ▼ 1 | Gemma 4 31B (Reasoning)OpenGoogle · 1 more variant | 15.4 | $0.000 | 35 | 1.0 s |
| 7 | ▲ 1 | Granite 4.2 30BOpenIBM | 14.8 | $0.28 | 77 | 0.8 s |
| 8 | ▲ 3 | Gemma 4 12B (Reasoning)OpenGoogle · 1 more variant | 14.2 | $0.15 | 110 | 2.4 s |
| 9 | ▲ 3 | Apriel-v1.5-15B-ThinkerOpenServiceNow | 13.8 | $0.000 | — | — |
| 10 | ▼ 1 | Nemotron 3.5 LightningOpenNVIDIA | 13.6 | $0.095 | 298 | 0.6 s |
| 11 | ▼ 4 | Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA | 13.6 | $0.31 | 171 | 2.8 s |
| 12 | ▲ 1 | Apriel-v1.6-15B-ThinkerOpenServiceNow | 13.4 | $0.000 | — | — |
| 13 | ▼ 3 | gpt-oss-120b (high)OpenOpenAI · 1 more variant | 12.3 | $0.26 | 217 | 0.8 s |
| 14 | — | Granite 4.2 8BOpenIBM | 11.8 | $0.11 | 83 | 0.6 s |
| 15 | — | Nemotron Cascade 2 30B A3BOpenNVIDIA | 11.7 | — | — | — |
| 16 | ▲ 2 | Nemotron 3 Nano Omni 30B A3B ReasoningOpenNVIDIA | 10.3 | $0.16 | — | — |
| 17 | — | gpt-oss-20b (low)OpenOpenAI · 1 more variant | 10.0 | $0.10 | 258 | 0.8 s |
| 18 | ▲ 3 | DiffusionGemma 26B A4BOpenGoogle | 9.5 | — | — | — |
| 19 | ▲ 1 | Llama 4 MaverickOpenMeta | 9.3 | $0.42 | 93 | 0.8 s |
| 20 | ▼ 4 | Granite 4.2 3BOpenIBM | 9.1 | $0.053 | 216 | 0.4 s |
| 21 | ▲ 1 | Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant | 9.0 | $0.40 | 84 | 4.7 s |
| 22 | ▲ 1 | Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant | 8.9 | — | — | — |
| 23 | ▲ 1 | Gemma 4 E4B (Reasoning)OpenGoogle · 1 more variant | 8.9 | $0.040 | 42 | 0.9 s |
| 24 | ▼ 5 | NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA · 1 more variant | 8.9 | $0.088 | 261 | 1.2 s |
| 25 | — | LFM2.5-2.6BOpenLiquid AI | 8.4 | $0.000 | — | — |
| 26 | ▲ 1 | Gemma 4 E2B (Reasoning)OpenGoogle · 1 more variant | 7.8 | — | — | — |
| 27 | ▲ 1 | Llama 3.3 Instruct 70BOpenMeta | 7.7 | $0.67 | 88 | 1.6 s |
| 28 | ▲ 1 | Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA | 7.5 | — | — | — |
| 29 | ▲ 1 | NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA · 1 more variant | 7.5 | $0.30 | 82 | 4.3 s |
| 30 | ▲ 1 | Granite 4.1 30BOpenIBM | 7.4 | — | — | — |
| 31 | ▲ 1 | NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA · 1 more variant | 7.4 | $0.070 | 96 | 5.6 s |
| 32 | ▲ 1 | NVIDIA Nemotron 3 Nano 4BOpenNVIDIA | 7.4 | — | — | — |
| 33 | ▲ 1 | Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA | 7.3 | — | — | — |
| 34 | ▲ 1 | Llama 3.1 Instruct 405BOpenMeta | 7.3 | — | — | — |
| 35 | ▲ 1 | LFM2.5-8B-A1BOpenLiquid AI | 7.2 | $0.000 | — | — |
| 36 | ▲ 1 | Llama 3.1 Nemotron Instruct 70BOpenNVIDIA | 6.9 | $1.2 | 91 | 4.3 s |
| 37 | ▲ 1 | Llama 3.1 Instruct 8BOpenMeta | 6.9 | $0.028 | 139 | 0.9 s |
| 38 | ▲ 2 | Llama 3.1 Instruct 70BOpenMeta | 6.6 | $0.56 | 55 | 1.7 s |
| 39 | ▲ 2 | Granite 4.1 8BOpenIBM | 6.6 | $0.063 | 126 | 0.8 s |
| 40 | ▼ 14 | Llama 4 ScoutOpenMeta | 6.5 | $0.31 | 119 | 0.8 s |
| 41 | ▲ 1 | R1 1776OpenPerplexity | 6.4 | — | — | — |
| 42 | — | Llama 3.2 Instruct 90B (Vision)OpenMeta | 6.4 | — | — | — |
| 43 | ▼ 1 | Phi-4 Mini InstructOpenMicrosoft | 6.3 | $0.000 | 45 | 0.9 s |
| 44 | ▼ 2 | Granite 4.0 H SmallOpenIBM | 6.0 | $0.11 | 12 | 33 s |
| 45 | ▼ 3 | LFM2 24B A2BOpenLiquid AI | 5.9 | — | — | — |
| 46 | ▼ 4 | Phi-4OpenMicrosoft | 5.9 | $0.22 | 39 | 2.6 s |
| 47 | ▼ 5 | Granite 4.1 3BOpenIBM | 5.9 | — | — | — |
| 48 | ▼ 6 | Phi-3 Mini Instruct 3.8BOpenMicrosoft | 5.8 | — | — | — |
| 49 | ▼ 7 | Gemma 3n E4B Instruct Preview (May '25)OpenGoogle | 5.8 | — | — | — |
| 50 | ▼ 8 | Phi-4 Multimodal InstructOpenMicrosoft | 5.8 | $0.000 | 17 | 0.9 s |
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