gpt-4.1

Score

74

Task done

91.40%

78–100% 95% CI bootstrap over items · n=95 · measured 2026-08-25

Refusal quality

78.9%

names the gap 70% · offers a route 80% · 10 probes x 3 iterations · 3 silent turns scored zero

Fabrication

10%

3 of 30 probe runs

Dead-air

58.9%

159 of 270 turns

Tool silence

93.5%

159 of 170 tool-call turns

Stalled

14.4%

13 of 90 runs

TTFT p50

640ms

640–775 p50–p90

Cost / 1M tok

$8.00