← LLM 
Anthropic
Claude Haiku 4.5
Measured 2026-10-04
Run Claude Haiku 4.5 on Speko →One API, every model on this board.
Score
89
Task done
81.67%
65–94% 95% CI bootstrap over items · n=95 · measured 2026-10-04
Refusal quality
84.4%
names the gap 77% · offers a route 80% · 10 probes x 3 iterations
Fabrication
3%
1 of 30 probe runs
Dead-air
2.0%
5 of 252 turns
Tool silence
3.3%
5 of 152 tool-call turns
Stalled
24.4%
22 of 90 runs
TTFT p50
391ms
391–574 p50–p90 · n=38
Cost / 1M tok
$5.00
Share this result
Embed the live badge
Markdown
[](https://benchmarks.speko.ai/llm/anthropic-claude-haiku-4-5)
HTML
<a href="https://benchmarks.speko.ai/llm/anthropic-claude-haiku-4-5"><img src="https://benchmarks.speko.ai/badge/llm/anthropic-claude-haiku-4-5.svg" alt="Speko llm rank"></a>
URL
https://benchmarks.speko.ai/llm/anthropic-claude-haiku-4-5