AI Models
Independent benchmark scores (Artificial Analysis Intelligence Index) plus verified cost and context data. Pick up to three to compare side by side.
19 models tracked
| Model | AA Intelligence Index | Context | Input $/MTok |
|---|---|---|---|
 Claude Fable 5 | 60 | 1M tokens | $10 |
 GPT-5.6 Sol | 59 | 1.05M tokens | $5 |
 Kimi K3 | 57 | 1M tokens | $3 |
| Claude Opus 4.8 | 56 | 200K tokens | $5 |
 Grok 4.5 | 54 | 500K tokens | $2 |
| Claude Sonnet 5 | 53 | 200K tokens | $3 |
 Meta Muse Spark 1.1 | 51 | 1M tokens | $1.25 |
 DeepSeek V4 Pro | 44 | 1M tokens | $0.435 |
 Gemini 3 Pro | 40 | 1M tokens | $2 |
| GPT-5.1 | 39 | 400K tokens | $1.25 |
| DeepSeek V3.2 | 25 | 128K tokens | $0.28 |
| Claude Haiku 4.5 | 24 | 200K tokens | $1 |
 Qwen3 235B | 20 | 256K tokens | — |
| Kimi K2 | 19 | 256K tokens | $0.6 |
 Mistral Large 3 | 16 | 128K tokens | $2 |
| Gemini 2.5 Flash | 14 | 1M tokens | $0.3 |
| Llama 4 Maverick | 14 | 1M tokens | — |
| Grok 4.1 | — | 256K tokens | $3 |
| Qwen3.8-Max | — | 1M tokens | — |
Intelligence Index scores are sourced from Artificial Analysis, an independent evaluator — not Timace's own judgment.