productivity benchmark
SpreadSheetBench-v1
SpreadSheetBench-v1 evaluates office automation agents on spreadsheet reasoning and manipulation tasks, measuring the ability to analyze, transform, and operate on spreadsheet data through tools.
Updated Aug 7, 2026
Published models3
Registry coverage3
MetricScore
EvidenceB
SpreadSheetBench-v1 leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | MI | 89.3% | 100.0% | 3 | C | |
| 2 | AC | 87.0% | 50.0% | 3 | C | |
| 3 | AC | 86.3% | 0.0% | 3 | C |
Score distribution
Top published rows on the benchmark's original scale.
SpreadSheetBench-v1 highlights
The top published results on this benchmark's own scale.
What is SpreadSheetBench-v1?
Definition and scoring fields from the benchmark registry.
SpreadSheetBench-v1 evaluates office automation agents on spreadsheet reasoning and manipulation tasks, measuring the ability to analyze, transform, and operate on spreadsheet data through tools.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- SpreadSheetBench-v1
- Modality
- text
- Primary category
- productivity
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- spreadsheetbench-v1|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about SpreadSheetBench-v1.
Which model scores highest on SpreadSheetBench-v1?
MiniMax M3 is currently ranked first with 89.3%.
What does SpreadSheetBench-v1 measure?
SpreadSheetBench-v1 evaluates office automation agents on spreadsheet reasoning and manipulation tasks, measuring the ability to analyze, transform, and operate on spreadsheet data through tools.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
3 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.