← LLM 
Anthropic
Claude Haiku 5.5
Measured 2026-10-08
Build voice agents on Speko →Claude Haiku 5.5 is measured here for comparison — it is not one of the models Speko routes.
Score
73
Task done
82.46%
65–96% 95% CI bootstrap over items · n=95 · measured 2026-10-08
Refusal quality
93.3%
names the gap 90% · offers a route 90% · 10 probes x 3 iterations
Fabrication
0%
0 of 10 probes (30 probe runs) · ≤31%
Dead-air
59.2%
177 of 299 turns
Tool silence
88.9%
177 of 199 tool-call turns
Stalled
16.7%
15 of 90 runs
TTFT p50
579ms
579–1157 p50–p90 · n=38
Cost / 1M tok
$0.50
Vendor list, per 1M output tokens ($0.10 in); prompts over 100K tokens bill $2.50 out.
Share this result
Embed the live badge
Markdown
[](https://benchmarks.speko.ai/llm/anthropic-claude-haiku-5-5)
HTML
<a href="https://benchmarks.speko.ai/llm/anthropic-claude-haiku-5-5"><img src="https://benchmarks.speko.ai/badge/llm/anthropic-claude-haiku-5-5.svg" alt="Speko llm rank"></a>
URL
https://benchmarks.speko.ai/llm/anthropic-claude-haiku-5-5