Compare / head-to-head
CodestralvsMistral Small 4
Codestral and Mistral Small 4 do not yet share a public benchmark, so quality cannot be compared apples-to-apples. Mistral Small 4 is 1.6x cheaper per token. Both offer a 256K-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0
no overlap yet
Cheaper per token
Mistral Small 4
1.6x cheaper, input + output
Larger context
Tie
both 256K tokens
Provider uptime (30d)
100%
Mistral AI
Codestral
Mistral AI · released 2025-01-13
text
Mistral Small 4
Mistral AI · released 2026-03-16
textvision
Quality
Benchmark matrix
0 shared · 1 only Codestral · 3 only Mistral Small 4| Benchmark | Codestral | Mistral Small 4 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 0 | ||||
| No public benchmark is reported for both models yet. | ||||
| Only Codestral reports · 1 | ||||
| HumanEval | 86.6% ↗ | not reported | — | — |
| Only Mistral Small 4 reports · 3 | ||||
| GPQA Diamond | not reported | 71.2% ↗ | — | — |
| MMLU-Pro | not reported | 78% ↗ | — | — |
| Artificial Analysis Long Context Reasoning | not reported | 0.72 ↗ | — | — |
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 Codestral minus Mistral Small 4 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 | Codestral | Mistral Small 4 | Edge |
|---|---|---|---|
| Context window | 256K tokens | 256K tokens | Tie |
| Max output | — | — | — |
| Input price / 1M | $0.3 ↗ | $0.15 ↗ | Mistral Small 4 |
| Output price / 1M | $0.9 ↗ | $0.6 ↗ | Mistral Small 4 |
| Cached input / 1M | $0.03 ↗ | $0.015 ↗ | Mistral Small 4 |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $1.2 | $0.75 | Mistral Small 4 |
| Modalities | text | text · vision | Mistral Small 4 |
| Released | 2025-01-13 | 2026-03-16 | — |
| Cited benchmark scores | 1 | 3 | — |
Reliability
Mistral AI status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Codestral vs …
Models sharing the most benchmarksMore matchups
Mistral Small 4 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Codestral and Mistral Small 4 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.