Models
A dated, category-by-category view of the model landscape.
Last validated snapshot
October 27, 2026
- Categories
- 25
- Available
- 21
- Ranked rows
- 67
Leaders and charts reflect the dated snapshot above. Source pools and rankings can change between snapshots. For live standings, visit Artificial Analysis .
Intelligence and token price
The frontier contains models that are not beaten by another option on both intelligence and a locally calculated 3:1 input-to-output token price. This price differs from the source site's blended price.
Models on the frontier
Ordered by intelligence index, highest first. Models with the same index and price share a point in the chart.
| Model | Intelligence index | Price / 1M tokens |
|---|---|---|
| Claude Opus 5.5 (Max, Default Fallback) | 57.6 | $8.00 |
| Claude Sonnet 5.5 (Max, Default Fallback) | 56.0 | $4.00 |
| GPT-6.1 Terra (Max) | 48.1 | $2.00 |
| Muse Spark 1.3 (Max) | 48.1 | $2.00 |
| MiMo-V2.6-Pro | 46.3 | $0.544 |
| DeepSeek V4.1 Flash 1017 (Max) | 45.1 | $0.525 |
| Ling 3.1 Flash 1019 | 43.9 | $0.45 |
| Claude Haiku 5.5 (Max) | 43.4 | $0.20 |
| MiMo-V2.6-Flash | 37.9 | $0.175 |
| Agnes 2.5 Pro Beta | 35.2 | $0.15 |
| DeepSeek V4 Flash 0420 (High) | 24.4 | $0.142 |
| Hy3-preview (Reasoning) | 22.7 | $0.10 |
| Qwen3.5 4B (Reasoning) | 13.1 | $0.06 |
| Granite 4.2 3B | 9.1 | $0.053 |
| Gemma 4 E4B (Reasoning) | 8.9 | $0.04 |
Leaders in this snapshot
View all categoriesOverall intelligence
704 of 715 eligible
Claude Opus 5.5 (Max, Default Fallback)
57.6
Coding
258 of 715 eligible
Claude Fable 5.1 (Max, Default Fallback)
81.6
Agentic
167 of 715 eligible
Claude Fable 5.1 (Max, Default Fallback)
57.9
Text-to-image
106 of 106 eligible
GPT Image 2.5 Sunburst (max)
1,222
Silent text-to-video
32 of 32 eligible
HeyGen Video 1
1,143
Text-to-speech
98 of 98 eligible
Eleven v4
1,334
Data source: Artificial Analysis .