Benchmarks

10 results across 6 benchmarks

Benchmark results for Mistral Small 4
BenchmarkScoreSource
GPQA DiamondEffort: None59.1%huggingface.co for Mistral Small 4 (none) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab)GPQA Diamond AccuracyReported Model cardMistral AISelf-reportedRecord for Mistral Small 4 on Graduate-Level Google-Proof Q&A Diamond
GPQA DiamondEffort: High71.2%huggingface.co for Mistral Small 4 (high) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab)GPQA Diamond AccuracyReported Model cardMistral AISelf-reportedRecord for Mistral Small 4 on Graduate-Level Google-Proof Q&A Diamond
IFBench OriginalEffort: None35.7%huggingface.co for Mistral Small 4 (none) on IFBench Original (opens in a new tab)AccuracyReported Model cardMistral AISelf-reportedRecord for Mistral Small 4 on IFBench Original
IFBench OriginalEffort: High48.0%huggingface.co for Mistral Small 4 (high) on IFBench Original (opens in a new tab)AccuracyReported Model cardMistral AISelf-reportedRecord for Mistral Small 4 on IFBench Original
MMLU-Pro OriginalEffort: None73.5%huggingface.co for Mistral Small 4 (none) on MMLU-Pro Original (opens in a new tab)AccuracyReported Model cardMistral AISelf-reportedRecord for Mistral Small 4 on MMLU-Pro Original
MMLU-Pro OriginalEffort: High78.0%huggingface.co for Mistral Small 4 (high) on MMLU-Pro Original (opens in a new tab)AccuracyReported Model cardMistral AISelf-reportedRecord for Mistral Small 4 on MMLU-Pro Original
MMMU-Pro No toolsEffort: NoneConfiguration: No tools46.3%huggingface.co for Mistral Small 4 (none) on MMMU-Pro No tools (opens in a new tab)MMMU-Pro accuracySetting: Not statedReported Model cardMistral AISelf-reportedRecord for Mistral Small 4 on MMMU-Pro No tools
MMMU-Pro No toolsEffort: HighConfiguration: No tools60.0%huggingface.co for Mistral Small 4 (high) on MMMU-Pro No tools (opens in a new tab)MMMU-Pro accuracySetting: Not statedReported Model cardMistral AISelf-reportedRecord for Mistral Small 4 on MMMU-Pro No tools
Terminal-Bench 2.0 — Vals AI Terminus 2Effort: HighConfiguration: Terminus-2 harness16.9%vals.ai for Mistral Small 4 (high) on Terminal-Bench 2.0 — Vals AI Terminus 2 (opens in a new tab)Archived copy (opens in a new tab)Terminal-Bench AccuracyReported Benchmark leaderboardVals AIIndependentRecord for Mistral Small 4 on Terminal-Bench 2.0 — Vals AI Terminus 2
Vibe Code Bench 1.1 — OpenHands, October 2026 evaluationEffort: HighConfiguration: OpenHands harness0.0%vals.ai for Mistral Small 4 (high) on Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation (opens in a new tab)Archived copy (opens in a new tab)Vibe Code Bench ScoreReported Benchmark leaderboardVals AIIndependentRecord for Mistral Small 4 on Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation