Opus 5.5
Anthropic · effort high · config opus-5-5-high-compact
- Overall
- 88
- Strict
- 54%
- $0.70 per solved task
- Human rank
- 54%
- Gate pass
- 93%
- Cost / task
- $0.38
- Time / task
- 1m 29s
Quality
Cost and time
Hard tasks
96
96
100
96
96
100
100
95
30
100
96
100
96
100
73
89
88
92
100
90
96
100
100
96
85
100
96
Failures
- Mesh rebuild blender handle: 3 of 3 attempts failed a gate
- Mesh rebuild freecad bracket: 2 of 3 attempts failed a gate
- Mesh socket mount: 1 of 3 attempts failed a gate
Run hard-compact-2026-10-162026-10-16commit 6fa9f854spend $116.04 + $54.69 AI judging, 1 unpricedOther runs: 2026-11-05T06-56-21-kimi31-sonnet-hard, 2026-11-05T05-50-12-kimi31-vs-sonnet, 2026-09-23T06-56-16-hard-baseline-2026-09-23, 2026-09-10T19-44-23-baseline-2026-09, 2026-09-04T20-02-10-stage2-hard-cases, 2026-09-04T19-48-31-screen-14-fixed