Model comparison
Mistral Small 4 vs Mistral Small 4 (Reasoning)
Head-to-head evidence from 16 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Sibling matchup inside the Mistral Small 4 family.
Public leaderboard positions: Mistral Small 4 #140 (Estimated); Mistral Small 4 (Reasoning) unranked (Not scored). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Mistral Small 4 and Mistral Small 4 (Reasoning) share 16 comparable benchmark results. 0 of 8 categories are comparable. 0 results are unique to Mistral Small 4; 0 to Mistral Small 4 (Reasoning).
Updated July 23, 2026- Shared results
- 16
- Mistral Small 4 only
- 0
- Mistral Small 4 (Reasoning) only
- 0
- Comparable categories
- 0 / 8
Benchmark data for Mistral Small 4 and Mistral Small 4 (Reasoning) is coming soon on BenchLM.
Confidence note. This is a partial-evidence comparison with 16 shared benchmark results across 6 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Mistral Small 4 | Mistral Small 4 (Reasoning) | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Mistral Small 4$0.15 input / $0.6 output | Mistral Small 4 (Reasoning)$0.15 input / $0.6 output | Listed prices are equal. |
| Generation speedtokens per second | Mistral Small 4175 tok/s | Mistral Small 4 (Reasoning)Not available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Mistral Small 40.64 s | Mistral Small 4 (Reasoning)Not available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Mistral Small 4256K | Mistral Small 4 (Reasoning)256K | Listed context windows are equal. |
Benchmark Deep Dive
Agentic4 benchmarks
Coding2 benchmarks
Reasoning2 benchmarks
Knowledge6 benchmarks
| Benchmark | Mistral Small 4 | Mistral Small 4 (Reasoning) | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | 19.6% | 19.6% | Tie |
| AA-GPQA DiamondSource | 76.9% | 76.9% | Tie |
| AA-HLESource | 9.5% | 9.5% | Tie |
| AA-Omniscience IndexSource | -29.9% | -29.9% | Tie |
| AA-Omniscience AccuracySource | 22.1% | 22.1% | Tie |
| AA-Omniscience Hallucination RateSource | 66.8% | 66.8% | Tie |
Multimodal1 benchmarks
| Benchmark | Mistral Small 4 | Mistral Small 4 (Reasoning) | Result |
|---|---|---|---|
| AA-MMMU-ProSource | 56.8% | 56.8% | Tie |
Inst. Following1 benchmarks
| Benchmark | Mistral Small 4 | Mistral Small 4 (Reasoning) | Result |
|---|---|---|---|
| AA-IFBenchSource | 48.2% | 48.2% | Tie |
Frequently Asked Questions (3)
Can I compare Mistral Small 4 and Mistral Small 4 (Reasoning) on BenchLM yet?
Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.
Why does this comparison show “coming soon”?
BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.
What data is available for Mistral Small 4 and Mistral Small 4 (Reasoning) today?
Mistral Small 4: $0.15 input / $0.60 output per 1M tokens Mistral Small 4 (Reasoning): $0.15 input / $0.60 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
Related Comparisons
Explore More
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.