GSM-Plus leaderboard
As of November 14, 2026, among the results listed here, SmolLM3-3B has the highest reported GSM-Plus score, 83.4 (Instruction Model; Extended Thinking), published by HuggingFaceTB. 1 model has a GSM-Plus result in our records.
Scores as the model makers published them, not re-run by us; each row links to its announcement.
Best reported score
83.4
Reported by HuggingFaceTB · Instruction Model; Extended Thinking
1 model ranked · 1 maker
| Rank | Model | Score | Setting | Reported by | Date |
|---|---|---|---|---|---|
| 1 | H SmolLM3-3B | 83.4 | Instruction Model; Extended Thinking | HuggingFaceTB | Publication date not reported |
Other reported runs
| Model | Score | Setting | Reported by | Date |
|---|---|---|---|---|
| H SmolLM3-3B | 72.8 | Instruction Model; No Extended Thinking | HuggingFaceTB | Publication date not reported |
How much to trust these numbers
- Source
- Reported by the model makers themselves. Not re-run by LLMBenchmark or anyone independent.
- Settings
- All ranked results use the same reported setting.
What GSM-Plus measures
GSM-Plus asks models to solve grade-school math problems with mathematical perturbations, with higher scores indicating more robust mathematical reasoning.