SVAMP
Unknown
1,000 elementary-level math word problems testing robustness of arithmetic reasoning.
Benchmark Stats
Models3
Papers3
Metrics1
SOTA History
Coming SoonVisual timeline of state-of-the-art progression over time will appear here.
accuracy
accuracy
Higher is better
| Rank | Model | Code | Score | Paper / Source |
|---|---|---|---|---|
| 1 | gpt-4o Simple Variations on Arithmetic Math word Problems. | - | 93.7 | arXiv Paper |
| 2 | claude-35-sonnet | - | 91.2 | arXiv Paper |
| 3 | llama-3-70b | HF | 89.5 | meta-blog |