Compare / head-to-head
Ministral 3 8BvsPhi-4 Mini Reasoning
Ministral 3 8B leads 1 of 1 shared benchmark. Ministral 3 8B has the larger context window (256K tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
1 – 0
Ministral 3 8B leads
Cheaper per token
—
list price, input + output
Larger context
Ministral 3 8B
256K tokens
Provider uptime (30d)
100% · —
Mistral AI · Microsoft
Ministral 3 8B
Mistral AI · released 2025-12-02
textvision
Phi-4 Mini Reasoning
Microsoft · released 2025-04-30
text
- Context
- 128K
- Max out
- 128K
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 3 · 2 core
Quality
Benchmark matrix
1 shared · 2 only Ministral 3 8B · 2 only Phi-4 Mini Reasoning| Benchmark | Ministral 3 8B | Phi-4 Mini Reasoning | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 1 | ||||
| GPQA Diamond | 66.8% ↗ | 52% ↗ | +14.8 pt | Ministral 3 8B |
| Only Ministral 3 8B reports · 2 | ||||
| AIME 2025 | 78.7% ↗ | not reported | — | — |
| LiveCodeBench | 61.6% ↗ | not reported | — | — |
| Only Phi-4 Mini Reasoning reports · 2 | ||||
| AIME 2024 | not reported | 57.5% ↗ | — | — |
| MATH-500 | not reported | 94.6% ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Ministral 3 8B minus Phi-4 Mini Reasoning in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | Ministral 3 8B | Phi-4 Mini Reasoning | Edge |
|---|---|---|---|
| Context window | 256K tokens | 128K tokens | Ministral 3 8B |
| Max output | — | 128K tokens | — |
| Input price / 1M | $0.15 ↗ | — | — |
| Output price / 1M | $0.15 ↗ | — | — |
| Cached input / 1M | $0.015 ↗ | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $0.3 | — | — |
| Modalities | text · vision | text | Ministral 3 8B |
| Released | 2025-12-02 | 2025-04-30 | — |
| Cited benchmark scores | 3 | 3 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Ministral 3 8B vs …
Models sharing the most benchmarksMore matchups
Phi-4 Mini Reasoning vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Ministral 3 8B and Phi-4 Mini Reasoning on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.