# Mistral Small 4 vs Raw Phi-4 mini direct logits

> Side-by-side benchmark comparison for Mistral Small 4 and Raw Phi-4 mini direct logits across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/mistral-small-4-vs-raw-phi-4-mini
- Last updated: October 1, 2026

- Shared sourced benchmarks: 0
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

No benchmark verdict yet: there is no shared sourced benchmark row for Mistral Small 4 and Raw Phi-4 mini direct logits.

## Summary

- Mistral Small 4 and Raw Phi-4 mini direct logits do not currently share a sourced benchmark row. The mirror therefore compares metadata, pricing, context windows, and each model's separately reported coverage without naming a benchmark winner.

## Model Snapshot

| Property | Mistral Small 4 | Raw Phi-4 mini direct logits |
|----------|----------|----------|
| Creator | Mistral | Microsoft |
| Type | Open Weight | Open Weight |
| Reasoning | Non-Reasoning | Non-Reasoning |
| Context | 256K | null |
| Independent public score (not head-to-head) | 35.08 | null |
| Benchmarks Covered | 0 | 2 |
| Pricing (input/output) | $0.15 / $0.60 | Pricing unavailable / Pricing unavailable |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- Mistral Small 4 public-lane score: 13.3 (Estimated · #107/119)
- Raw Phi-4 mini direct logits public-lane score: Coming soon

### Coding

- Winner: Insufficient shared evidence
- Mistral Small 4 public-lane score: 21.4 (Estimated · #117/144)
- Raw Phi-4 mini direct logits public-lane score: Coming soon

### Reasoning

- Winner: Insufficient shared evidence
- Mistral Small 4 public-lane score: 56.4 (Unranked · 2 rankable rows)
- Raw Phi-4 mini direct logits public-lane score: Coming soon

| Benchmark | Mistral Small 4 | Raw Phi-4 mini direct logits | Winner |
|-----------|-----------|-----------|--------|
| JevBench 1.4 | Coming soon | 37.96 | Coming soon |
| JevBench 1.5 | Coming soon | 15.22 | Coming soon |

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- Mistral Small 4 public-lane score: 44.8 (Unranked · 1 rankable row)
- Raw Phi-4 mini direct logits public-lane score: Coming soon

### Knowledge

- Winner: Insufficient shared evidence
- Mistral Small 4 public-lane score: 32.9 (Estimated · #124/170)
- Raw Phi-4 mini direct logits public-lane score: Coming soon

### Instruction Following

- Winner: Insufficient shared evidence
- Mistral Small 4 public-lane score: 55.7 (#77/124)
- Raw Phi-4 mini direct logits public-lane score: Coming soon

## FAQ

### Can I compare Mistral Small 4 and Raw Phi-4 mini direct logits on BenchLM yet?

Not fully yet. BenchLM is tracking both models, but sourced benchmark coverage is still incomplete for a fair score-level comparison.

### Why does this page show "coming soon" values?

BenchLM only calls winners when public benchmark coverage is available on both sides of the comparison.

## Related Comparisons

- [Mistral Small 4 vs Mistral Small 4 (Reasoning)](/compare/mistral-small-4-vs-mistral-small-4-reasoning)
- [Raw Phi-4 mini direct logits vs Mistral Small 4 (Reasoning)](/compare/mistral-small-4-reasoning-vs-raw-phi-4-mini)
- [Mistral Small 4 vs GPT-6 Astra](/compare/gpt-6-astra-vs-mistral-small-4)
- [Raw Phi-4 mini direct logits vs GPT-6 Astra](/compare/gpt-6-astra-vs-raw-phi-4-mini)

## Explore More

- [Mistral Small 4 profile](/models/mistral-small-4)
- [Raw Phi-4 mini direct logits profile](/models/raw-phi-4-mini)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)