Gemini 3.8 Flash
Google · config gemini-3-8-flash
- Overall
- 93
- Strict
- 71%
- $0.23 per solved task
- Human rank
- 61%
- Gate pass
- 96%
- Cost / task
- $0.16
- Time / task
- 1m 18s
Quality
Cost and time
Easy tasks
100
100
100
100
100
100
100
100
100
100
100
95
100
100
100
100
100
100
100
100
Medium tasks
96
100
100
93
75
75
100
96
37
100
Hard tasks
100
100
100
100
100
100
100
30
100
100
100
100
100
78
92
88
87
100
87
100
100
96
83
100
94
Failures
- Mesh rebuild blender handle: 3 of 3 attempts failed a gate
- Vendored nema17 mount: 2 of 2 attempts failed a gate
Run baseline-2026-092026-09-10commit 41aec7daspend $339.70 + $48.02 AI judging, 7 unpricedOther runs: 2026-09-04T20-02-10-stage2-hard-cases, 2026-09-04T19-48-31-screen-14-fixed