Claude haiku 4.5
Claude Haiku 4.5 is Anthropic's fastest efficient model, delivering near-frontier intelligence. It matches Sonnet 4's performance in reasoning and coding, optimized for real-time applications.
Leaderboards
QUALITY
Average Score combining domain-specific Autobench scores; Higher is better
- 4.27
- 4.49
- 4.45
- 4.37
- 4.37
- 4.34
- 4.32
- 4.30
- 4.27
- 4.25
- 4.23
- 4.21
- 4.17
- 4.08
- 3.70
- 3.70
- 3.61
- 3.46
- 3.35
PRICE
USD cent per average answer; Lower is better
- 1.88
- 0.01
- 0.03
- 0.05
- 0.06
- 0.07
- 0.10
- 0.17
- 0.17
- 0.26
- 0.58
- 0.83
- 0.91
- 0.98
- 1.42
- 4.84
- 7.53
- 7.71
- 15.44
LATENCY
Average Latency in Seconds; Lower is better
- 41.83s
- 6.62s
- 13.00s
- 13.16s
- 14.38s
- 17.14s
- 17.49s
- 17.88s
- 18.39s
- 19.90s
- 23.30s
- 24.98s
- 36.21s
- 40.03s
- 43.38s
- 45.14s
- 45.45s
- 54.51s
- 58.05s
- 63.81s
- 68.67s
- 85.92s
- 99.89s
- 100.48s
- 107.45s
- 113.96s
- 129.78s
- 151.90s
Performance vs. Industry Average
Intelligence
Claude haiku 4.5 is of higher intelligence compared to average (4.1), with an intelligence score of 4.3.
Price
Claude haiku 4.5 is more expensive compared to average ($1.68 per 1M Tokens) with a price of $1.88 per 1M Tokens.
Latency
Claude haiku 4.5 has a lower average latency compared to average (53.05s), with an average latency of 41.70s.
P99 Latency
Claude haiku 4.5 has a lower P99 latency compared to average (187.12s), taking 165.87s to receive the first token at P99 (TTFT).
Context Window
Claude haiku 4.5 has a smaller context window than average (339k tokens), with a context window of 200k tokens.