Strict Task Zeroed
Severity 8/10
2026-W39
Gemini 2.5 Pro 综合 Strict Question Zeroed
Score Comparison
| Dimension | Previous | Current | Change |
|---|---|---|---|
| Overall (v5) | 61.4 | 64.1 | +2.7 |
| Code Execution (v5) | 53.1 | 65.7 | +12.6 |
| Knowledge Synthesis (v5) | 83.6 | 75.2 | -8.4 |
| Grounding (v5) | 66.1 | 72.8 | +6.7 |
| Value | 34.6 | 36.3 | +1.7 |
| Stability | 28.9 | 35.2 | +6.3 |
| Availability | 92.0 | 90.0 | -2 |
Affected Dimensions
execution
Top Lost Tasks 1
#1
增值税发票含税反算与逐行对账（4个舍入陷阱）
100
0
Run #333 · Formula v7 · Judge v6.4 · Benchmark v7 · 2026-09-21 05:05 SGT
View Gemini 2.5 Pro Full Profile