Compare / head-to-head
Devstral 2vsDevstral Small 2
Devstral 2 leads 3 of 3 shared benchmarks. Devstral Small 2 is 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
3 – 0
Devstral 2 leads
Cheaper per token
Devstral Small 2
6x cheaper, input + output
Larger context
Tie
both 256K tokens
Providers
Mistral AI
same provider
Devstral 2
Mistral AI · released 2025-12-09
text
Devstral Small 2
Mistral AI · released 2025-12-09
textvision
Quality
Benchmark matrix
3 shared · 1 only Devstral 2 · 0 only Devstral Small 2| Benchmark | Devstral 2 | Devstral Small 2 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 3 | ||||
| SWE-bench Verified | 72.2% ↗ | 68% ↗ | +4.2 pt | Devstral 2 |
| SWE-bench Multilingual | 61.3% ↗ | 55.7% ↗ | +5.6 pt | Devstral 2 |
| Terminal Bench 2 | 32.6% ↗ | 22.5% ↗ | +10.1 pt | Devstral 2 |
| Only Devstral 2 reports · 1 | ||||
| LMArena WebDev (LMArena) | 1196.1 ↗ | not reported | — | — |
| Only Devstral Small 2 reports · 0 | ||||
| Devstral Small 2 reports nothing Devstral 2 does not. | ||||
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 Devstral 2 minus Devstral Small 2 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 | Devstral 2 | Devstral Small 2 | Edge |
|---|---|---|---|
| Context window | 256K tokens | 256K tokens | Tie |
| Max output | — | — | — |
| Input price / 1M | $0.4 ↗ | $0.1 ↗ | Devstral Small 2 |
| Output price / 1M | $2 ↗ | $0.3 ↗ | Devstral Small 2 |
| Cached input / 1M | — | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $2.4 | $0.4 | Devstral Small 2 |
| Modalities | text | text · vision | Devstral Small 2 |
| Released | 2025-12-09 | 2025-12-09 | — |
| Cited benchmark scores | 4 | 3 | — |
Reliability
Mistral AI status
Live from /statusMore matchups
Devstral 2 vs …
Models sharing the most benchmarksMore matchups
Devstral Small 2 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Devstral 2 and Devstral Small 2 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.