MixEval Hard leaderboard
As of November 14, 2026, among the results listed here, SmolLM3-3B has the highest reported MixEval Hard score, 30.8 (Instruction Model; Extended Thinking), published by HuggingFaceTB. 1 model has a MixEval Hard 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
30.8
Reported by HuggingFaceTB · Instruction Model; Extended Thinking
1 model ranked · 1 maker
| Rank | Model | Score | Setting | Reported by | Date |
|---|---|---|---|---|---|
| 1 | H SmolLM3-3B | 30.8 | Instruction Model; Extended Thinking | HuggingFaceTB | Publication date not reported |
Other reported runs
| Model | Score | Setting | Reported by | Date |
|---|---|---|---|---|
| H SmolLM3-3B | 26.9 | 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 MixEval Hard measures
MixEval Hard appears in the release announcements of HuggingFaceTB. We have not found a public write-up of the benchmark itself yet.