← LLM 
Anthropic
Claude Sonnet 5
Measured 2026-10-04
Run Claude Sonnet 5 on Speko →One API, every model on this board.
Score
59
Task done
83.33%
68–95% 95% CI bootstrap over items · n=95 · measured 2026-10-04
Refusal quality
90.0%
names the gap 77% · offers a route 93% · 10 probes x 3 iterations
Fabrication
0%
0 of 10 probes (30 probe runs) · ≤31%
Dead-air
34.6%
101 of 292 turns
Tool silence
52.6%
101 of 192 tool-call turns
Stalled
18.9%
17 of 90 runs
TTFT p50
1.47s
1.47–2.74s p50–p90 · n=38
Cost / 1M tok
$10.00
Introductory rate through 2026-08-31; $15.00 from 2026-09-01.
Share this result
Embed the live badge
Markdown
[](https://benchmarks.speko.ai/llm/anthropic-claude-sonnet-5)
HTML
<a href="https://benchmarks.speko.ai/llm/anthropic-claude-sonnet-5"><img src="https://benchmarks.speko.ai/badge/llm/anthropic-claude-sonnet-5.svg" alt="Speko llm rank"></a>
URL
https://benchmarks.speko.ai/llm/anthropic-claude-sonnet-5