SpreadSheetBench-v1
Category
General Agents
Max Score
100.0
Score Type
percent
Active
Yes
Model Scores
Scores for SpreadSheetBench-v1
| Model | Score | Date | Verified |
|---|---|---|---|
| GLM 5.1 Thinking |
92.31%
|
11.06.2026 | Unverified |
| GPT 5.5 |
97.62%
|
11.06.2026 | Unverified |
| Kimi K2.6 |
91.03%
|
11.06.2026 | Unverified |
| MiniMax-M2.7 |
91.76%
|
11.06.2026 | Unverified |
| DeepSeek V4 Pro |
91.76%
|
11.06.2026 | Unverified |
| Claude Opus 4.7 |
98.35%
|
11.06.2026 | Unverified |
| MiniMax-M3 |
100.00%
|
11.06.2026 | Unverified |
| Gemini 3.1 Pro |
39.01%
|
11.06.2026 | Unverified |
| Kimi K3 |
34.80
|
18.08.2026 | Verified |