Reasoning
Mathematical and scientific problem solving.
Score and research range
- Full-precision point
- 101.39025883006508
- Range
- 98.77–104.01 · 90% Research Range
- Scope
- Conditional fuller R0 A
Score includes qualified prediction of missing evidence.
Model profile / Mistral AI
Mistral AI's open hybrid model combining instruction following, reasoning and coding.
Four areas of evidence
Mathematical and scientific problem solving.
Score includes qualified prediction of missing evidence.
Software engineering and programming.
Factual reliability and instruction following.
Tool use, workflows and professional tasks.
Current index snapshot · 2026-09-16. Each category uses its own scale; scores across categories are not directly comparable. Evidence counts describe the retained Capabilities inputs; a family can contain several tasks or configurations. A point lead does not establish superiority.
Performance in context
Mistral Small 4 is highlighted wherever a compatible measurement is available.
Lumina Capabilities Index
The current Capabilities cohort, with this model highlighted.
Chart loads as you explore
Lumina Capabilities Index
The current Capabilities cohort, with this model highlighted.
Chart loads as you explore
Explore the detail
Score uses the admitted direct native evidence under the selected method.
Score includes qualified prediction of missing evidence.
| Benchmark | Result | Published configuration | Source |
|---|---|---|---|
| AA Long Context Reasoningstandard | 47.333% | Mistral Small 4 (Reasoning) (Artificial Analysis completed independent run)Artificial Analysis AA-LCR evaluation | Mistral Small 4 (Reasoning) current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29independently-verified · ranking-eligible |
| CritPtstandard | 0.286% | Mistral Small 4 (Reasoning) (Artificial Analysis completed independent run)Artificial Analysis CritPt evaluation | Mistral Small 4 (Reasoning) current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29independently-verified · ranking-eligible |
| GDPval-AA v2v2 | 4.498% | Mistral Small 4 (Reasoning) (Artificial Analysis completed independent run)Artificial Analysis GDPval-AA v2 | Mistral Small 4 (Reasoning) current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29independently-verified · ranking-eligible |
| GPQA Diamonddiamond | 76.869% | Mistral Small 4 (Reasoning) (Artificial Analysis completed independent run)Artificial Analysis GPQA Diamond evaluation | Mistral Small 4 (Reasoning) current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29independently-verified · ranking-eligible |
| Humanity's Last Examtext-only current | 9.87% | Mistral Small 4 (Reasoning) (Artificial Analysis completed independent run)Artificial Analysis text-only HLE evaluation | Mistral Small 4 (Reasoning) current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29independently-verified · ranking-eligible |
| SciCode2024 | 37.963% | Mistral Small 4 (Reasoning) (Artificial Analysis completed independent run)Artificial Analysis SciCode evaluation | Mistral Small 4 (Reasoning) current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29independently-verified · reference-only |
| τ³-Banking3 | 4.948% | Mistral Small 4 (Reasoning) (Artificial Analysis completed independent run)Artificial Analysis tau3-Banking evaluation | Mistral Small 4 (Reasoning) current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29independently-verified · ranking-eligible |
| Terminal-Bench2.1 | 20.974% | Mistral Small 4 (Reasoning) (Artificial Analysis completed independent run)Artificial Analysis Terminal-Bench v2.1 in e2b | Mistral Small 4 (Reasoning) current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29independently-verified · ranking-eligible |
| Artificial Analysis Agentic Index2026 | 4.7 index | Exact BenchLM registry variant Mistral Small 4; bulk export does not retain a complete upstream harness configuration.Source-native system | BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21source-checked · reference-only |
| Artificial Analysis Agentic Index2026 | 4.7 index | Exact BenchLM registry variant Mistral Small 4; bulk export does not retain a complete upstream harness configuration.Source-native system | BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27source-checked · reference-only |