Model profile
Mistral Small 4
Evidence summary
Mistral Small 4 has an estimated overall rank of #217; its 90% source-sensitivity interval is #132–#244. Its behavior-only rank is #208; company governance moves the combined estimate to #217. Published evidence spans 4 evals and 4 of 7 behavior components. Its strongest relative result is SM-Bench (eq_boundaries, #2 of 73); its weakest is SM-Bench (anti_hallucination, #72 of 73).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗mistral-small-4
- Hugging Face ↗mistralai/Mistral-Small-4-119B-2603
- OpenRouter ↗mistralai/mistral-small-2603
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗repository created at proxy
Published eval results
Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Better | Source |
|---|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #87 / 311 | 0.6679 | ↓ lower | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #97 / 105 | 0.05 | ↑ higher | Source ↗official | |
| DystopiaBenchbasaglia_score | #35 / 50 | 68.57 | ↓ lower | Source ↗official | |
| DystopiaBenchbaudrillard_score | #49 / 50 | 80 | ↓ lower | Source ↗official | |
| DystopiaBenchhuxley_score | #40 / 50 | 76.17 | ↓ lower | Source ↗official | |
| DystopiaBenchlaguardia_score | #29 / 50 | 67.9 | ↓ lower | Source ↗official | |
| DystopiaBenchorwell_score | #35 / 50 | 73.53 | ↓ lower | Source ↗official | |
| DystopiaBenchpetrov_score | #44 / 50 | 80.37 | ↓ lower | Source ↗official | |
| SM-Benchadversarial | #71 / 73 | 69.27 | ↑ higher | Source ↗official | |
| SM-Benchambiguous_interpretation | #70 / 73 | 62.5 | ↑ higher | Source ↗official | |
| SM-Benchanti_hallucination | #72 / 73 | 57.85 | ↑ higher | Source ↗official | |
| SM-Bencheq_boundaries | #2 / 73 | 85.67 | ↑ higher | Source ↗official | |
| SM-Benchoverfit | #48 / 73 | 62.57 | ↑ higher | Source ↗official |
Values evaluations
Descriptive values and political-framing results are separate from safety/ethics ranks. Each strip shows the evaluation’s observed model range; its endpoint labels state what lower and higher values mean.