Compare / head-to-head
Devstral Small 2vs
Gemini 4 Argon
Devstral Small 2 and Gemini 4 Argon do not yet share a public benchmark, so quality cannot be compared apples-to-apples. Devstral Small 2 is 30x cheaper per token.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0
no overlap yet
Cheaper per token
Devstral Small 2
30x cheaper, input + output
Larger context
—
both 256K tokens
Providers
2 providers
Mistral AI · Google
Devstral Small 2
Mistral AI · released 2025-12-09
textvision
Gemini 4 Argon
Google · released 2026-09-30
textvisionvideo
Quality
Benchmark matrix
0 shared · 3 only Devstral Small 2 · 12 only Gemini 4 Argon| Benchmark | Devstral Small 2 | Gemini 4 Argon | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 0 | ||||
| No public benchmark is reported for both models yet. | ||||
| Only Devstral Small 2 reports · 3 | ||||
| SWE-bench Verified | 68% ↗ | not reported | — | — |
| SWE-bench Multilingual | 55.7% ↗ | not reported | — | — |
| Terminal Bench 2 | 22.5% ↗ | not reported | — | — |
| Only Gemini 4 Argon reports · 12 | ||||
| LMArena Elo | not reported | 1525.2 ↗ | — | — |
| APEX-Agents (Mercor) | not reported | 82.2% ↗ | — | — |
| AutomationBench | not reported | 51.3% ↗ | — | — |
| CWE-bench v1 | not reported | 68% ↗ | — | — |
| DeepSWE v1.1 | not reported | 77.9% ↗ | — | — |
| FrontierSWE V2 (Proximal Labs) | not reported | 55% ↗ | — | — |
| LMArena Agent (LMArena) | not reported | 0.0757 ↗ | — | — |
| LMArena WebDev (LMArena) | not reported | 1679.5 ↗ | — | — |
| LVBench | not reported | 91.7% ↗ | — | — |
| SAGE (Vals AI) | not reported | 53.6% ↗ | — | — |
| Terminal-Bench 4.0 (Vals AI) | not reported | 57.6% ↗ | — | — |
| Vending-Bench 2 (Andon Labs) | not reported | 13718.16 ↗ | — | — |
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 Small 2 minus Gemini 4 Argon 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 Small 2 | Gemini 4 Argon | Edge |
|---|---|---|---|
| Context window | 256K tokens | — | — |
| Max output | — | 1M tokens | — |
| Input price / 1M | $0.1 ↗ | $2 ↗ | Devstral Small 2 |
| Output price / 1M | $0.3 ↗ | $10 ↗ | Devstral Small 2 |
| Cached input / 1M | — | $0.1 ↗ | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $0.4 | $12 | Devstral Small 2 |
| Modalities | text · vision | text · vision · video | Gemini 4 Argon |
| Released | 2025-12-09 | 2026-09-30 | — |
| Cited benchmark scores | 3 | 12 | — |
Reliability
Provider status
Live from /statusMore matchups
Devstral Small 2 vs …
Models sharing the most benchmarksMore matchups
Gemini 4 Argon vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Devstral Small 2 and Gemini 4 Argon on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.