Capability index
27 models across 10 providers. Seed scores are the floor — probe measurements and real routing outcomes replace them, and the ledger only grows.
📡 Model Radar · the market, watched daily
Reading the market feed…
Probe a model — probe suite v1, objective scoring, costs cents on your key, updates your routing instantly.
| Model | Provider | Avg capability | Best for | Context | Speed | Cost / call* |
|---|---|---|---|---|---|---|
| Claude Fable 5 | Anthropic | 96 | Code / review, Hard reasoning / analysis | 1000K | 40 | $0.040 |
| GPT-5.6 Sol | OpenAI | 95 | Hard reasoning / analysis, Summarize | 1050K | 60 | $0.008 |
| Claude Opus 4.8 | Anthropic | 95 | Code / review, Writing / marketing | 200K | 45 | $0.020 |
| Claude Opus 5 | Anthropic | 95 | Code / review, Writing / marketing | 1000K | 50 | $0.020 |
| GPT-5.5 | OpenAI | 94 | Hard reasoning / analysis, Summarize | 1050K | 60 | $0.022 |
| Kimi K3open | Moonshot | 94 | Research / long context, Code / review | 1000K | 45 | $0.012 |
| Claude Sonnet 5 | Anthropic | 93 | Code / review, Summarize | 1000K | 90 | $0.008 |
| GPT-5.6 Terra | OpenAI | 93 | Hard reasoning / analysis, Classify / route | 1050K | 80 | $0.009 |
| GPT-5.2 | OpenAI | 93 | Hard reasoning / analysis, Classify / route | 400K | 60 | $0.010 |
| Gemini 3.1 Pro | 93 | Research / long context, Summarize | 1000K | 70 | $0.009 | |
| GPT-5 | OpenAI | 93 | Hard reasoning / analysis, Classify / route | 400K | 60 | $0.007 |
| Claude Sonnet 4.6 | Anthropic | 92 | Code / review, Summarize | 200K | 90 | $0.012 |
| Grok 4.6 | xAI | 92 | Hard reasoning / analysis, Classify / route | 500K | 80 | $0.006 |
| Gemini 2.5 Pro | 90 | Research / long context, Summarize | 1000K | 70 | $0.007 | |
| DeepSeek V4 Proopen | DeepSeek | 90 | Hard reasoning / analysis, Code / review | 1000K | 70 | $0.002 |
| Gemini 3.7 Flash | 89 | Research / long context, Classify / route | 1000K | 180 | $0.003 | |
| GLM 5.3open | Z.ai | 89 | Code / review, Classify / route | 1310K | 100 | $0.004 |
| Gemini 3.6 Flash | 88 | Research / long context, Classify / route | 1000K | 180 | $0.003 | |
| GPT-5.6 Luna | OpenAI | 87 | Classify / route, Extract structured data | 1050K | 140 | $0.001 |
| Mistral Large 3 | Mistral | 86 | Classify / route, Extract structured data | 262K | 110 | $0.002 |
| DeepSeek V4 Flashopen | DeepSeek | 86 | Classify / route, Extract structured data | 1000K | 120 | $0.001 |
| Gemini 2.5 Flash | 85 | Research / long context, Classify / route | 1000K | 180 | $0.002 | |
| GPT-5 mini | OpenAI | 85 | Classify / route, Extract structured data | 400K | 120 | $0.001 |
| Grok 4.1 Fast | xAI | 85 | Classify / route, Extract structured data | 256K | 160 | $0.001 |
| Claude Haiku 4.5 | Anthropic | 85 | Classify / route, Extract structured data | 200K | 160 | $0.004 |
| Qwen 3 Maxopen | Alibaba | 85 | Classify / route, Extract structured data | 256K | 120 | $0.003 |
| Llama 4 Maverickopen | Meta | 82 | Classify / route, Extract structured data | 256K | 130 | $0.001 |
*Representative 1,500-in / 500-out call. Prices illustrative — refresh from provider price lists.