Anthropic
Claude Haiku 5.5
ReasoningClosed weights
- Intelligence
- 41.2
- Rank 57 of 744 measured models
- Output speed
- 181 t/s
- Rank 46 of 403 measured models
- Price/1M
- $0.20
- Rank 161 of 659 measured models
- Context window
- 1M
- Rank 84 of 1199 measured models
- Cost per task
- $0.124
- Rank 59 of 193 measured models
Claude Haiku 5.5 (Xhigh) scores 41.2 on the Artificial Analysis Intelligence Index, ranking 57th of 744 measured models. The closest models on this index are Ling 3.1 Flash (41.1), Gemini 3.8 Flash (40.9), and Claude Opus 4.7 (40.7). At $0.20 per million tokens (3:1 input/output blended price), it is cheaper than Ling 3.1 Flash ($0.45), Gemini 3.8 Flash ($1.50), and Claude Opus 4.7 ($10). With an output speed of 181 t/s, it is faster than Gemini 3.8 Flash (140 t/s) and Claude Opus 4.7 (52.9 t/s), slower than Ling 3.1 Flash (211 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Claude Opus 4.8 (batch)
Anthropic · — · —
41.8+0.6——Compare - Ling 3.1 Flash
InclusionAI · $0.45 · 211 t/s
41.1−0.1$0.45211 t/sCompare - Gemini 3.8 Flash
Google · $1.50 · 140 t/s
40.9−0.3$1.50140 t/sCompare - Claude Opus 4.7
Anthropic · $10 · 52.9 t/s
40.7−0.5$1052.9 t/sCompare
