AnthropicClosed
Claude 4.5 Haiku (Reasoning)
Ranking metrics for Claude 4.5 Haiku (Reasoning): benchmark score, API price, output speed, and provider context.
Release date
Oct 15, 2025
Rank
#77
Intelligence Index
29.9
Blended API price
$0.770 / 1M tokens
Output speed
91.8 tok/s
Sources
- Artificial Analysis ranking data / Artificial Analysis / accessed 2026-08-09
- Artificial Analysis methodology / Artificial Analysis / accessed 2026-08-09
- Artificial Analysis model profile / Anthropic / accessed 2026-08-09
Benchmark board
Model ranking
Rank, model, provider, Artificial Analysis Intelligence Index, blended API price, and output speed.
| Rank | Model | Provider | Index | Blended price | Speed |
|---|---|---|---|---|---|
| #1 | Claude Opus 5 (Adaptive Reasoning, Max Effort) | Anthropic | 63.1 | $3.850/M | 57.6 tok/s |
| #2 | Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) | Anthropic | 62.5 | $3.850/M | 60.6 tok/s |
| #3 | Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) | Anthropic | 62.1 | $7.700/M | 69.7 tok/s |
| #4 | Claude Opus 5 (Adaptive Reasoning, High Effort) | Anthropic | 61.5 | $3.850/M | 61.0 tok/s |
| #8 | Claude Opus 5 (Adaptive Reasoning, Medium Effort) | Anthropic | 58.6 | $3.850/M | 59.3 tok/s |
| #15 | Claude Sonnet 5 (Adaptive Reasoning, Max Effort) | Anthropic | 55.3 | $1.540/M | 72.0 tok/s |
| #18 | Claude Opus 5 (Adaptive Reasoning, Low Effort) | Anthropic | 52.5 | $3.850/M | 58.3 tok/s |
| #37 | Claude Sonnet 5 (Non-reasoning, High Effort) | Anthropic | 42.6 | $1.540/M | 72.1 tok/s |
| #58 | Claude Sonnet 4.6 (Non-reasoning, Low Effort) | Anthropic | 35.1 | $2.310/M | 43.8 tok/s |
| #77 | Claude 4.5 Haiku (Reasoning) | Anthropic | 29.9 | $0.770/M | 91.8 tok/s |