AI MODEL INDEX
Latest AI model performance and cost
Compare an independent intelligence index with cost per benchmark task, including token usage.
Snapshot: September 11, 2026
Latest model intelligence index
Representative reasoning setting per model · higher is better
Selected model detailsClaude Fable 5.1Anthropic · max · fallback
- Index
- 53
- Per task
- $7.63
- Output speed
- 67 t/s
- Context
- 1M
Intelligence vs cost per task
Models closer to the upper-left deliver more intelligence at lower task cost
Selected model detailsClaude Fable 5.1Anthropic · max · fallback
- Index
- 53
- Per task
- $7.63
- Output speed
- 67 t/s
- Context
- 1M
| Model | Setting | Index | Cost/task | Output speed | Context |
|---|---|---|---|---|---|
| Claude Fable 5.1Anthropic | max · fallback | 53 | $7.63 | 67 t/s | 1M |
| GPT-6 AstraOpenAI | max | 53 | $3.26 | 54 t/s | 1M |
| Claude Opus 5Anthropic | max | 51 | $5.86 | 51 t/s | 1M |
| Muse Spark 1.3Meta | max | 48 | $1.60 | 197 t/s | 1M |
| GLM-5.3Z AI | max | 45 | $2.01 | 58 t/s | 1M |
| Grok 4.6xAI | high | 44 | $1.86 | 53 t/s | 500K |
| GPT-5.6 TerraOpenAI | max | 42 | $1.40 | 82 t/s | 1M |
| Gemini 3.8 FlashGoogle | high | 41 | $1.24 | 268 t/s | 1M |
| Claude Sonnet 5Anthropic | max | 38 | $5.09 | 75 t/s | 1M |
| GPT-5.6 LunaOpenAI | max | 38 | $0.18 | 109 t/s | 1M |