Model comparison
Devstral Small 2505 vs Gemini 4 Argon
Gemini 4 Argon is the stronger model overall, scoring 56.5 to 34.3 on the Noometry Index.
Last verified . 2 shared benchmarks.
Mistral AI
GoogleSummary
- They share 2 benchmarks with published results for both. Devstral Small 2505 scores higher in 0 categories and Gemini 4 Argon in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 4 Argon leads 44.2 to 19.7.
- The biggest single-benchmark swing is SciCode: 28.8% for Devstral Small 2505 and 61.8% for Gemini 4 Argon.
- Devstral Small 2505 has downloadable open weights; the other is API-only.
Side by side
| Devstral Small 2505 | Gemini 4 Argon | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 34.3 | 56.5 |
| Released | 2025-05-07 | 2026-09-30 |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.30 | — |
| Results tracked | 4 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 4 Argon leads
Devstral Small 2505: 38.9 (#166), Gemini 4 Argon: 62.0 (#9)
| Benchmark | Devstral Small 2505 | Gemini 4 Argon |
|---|---|---|
| SciCode | 28.8% | 61.8% |
| SWE-bench Verified (bash only) | 56.4% | — |
| LMArena WebDev | — | 1678 |
| FrontierSWE | — | 55% |
| LMArena Coding | — | 1550 |
Agentic & Tool Use Not comparable
Devstral Small 2505: —, Gemini 4 Argon: 49.2 (#8)
| Benchmark | Devstral Small 2505 | Gemini 4 Argon |
|---|---|---|
| APEX-Agents | — | 82.2% |
| Vending-Bench 2 | — | 13,718 |
Reasoning Gemini 4 Argon leads
Devstral Small 2505: 19.7 (#252), Gemini 4 Argon: 44.2 (#47)
| Benchmark | Devstral Small 2505 | Gemini 4 Argon |
|---|---|---|
| CritPt | 0% | 27.1% |
| Kagi LLM Benchmark | 37.7% | — |
| LMArena Hard Prompts | — | 1548 |
Math Not comparable
Devstral Small 2505: —, Gemini 4 Argon: 73.9 (#17)
| Benchmark | Devstral Small 2505 | Gemini 4 Argon |
|---|---|---|
| ProofBench | — | 99% |
| LMArena Math | — | 1536 |
Knowledge Not comparable
Devstral Small 2505: —, Gemini 4 Argon: 43.9 (#89)
| Benchmark | Devstral Small 2505 | Gemini 4 Argon |
|---|---|---|
| LMArena Expert | — | 1553 |
Multimodal Not comparable
Devstral Small 2505: —, Gemini 4 Argon: 46.5 (#14)
| Benchmark | Devstral Small 2505 | Gemini 4 Argon |
|---|---|---|
| Blueprint-Bench 2 | — | 54.4% |
Multilingual Not comparable
Devstral Small 2505: —, Gemini 4 Argon: 60.3 (#1)
| Benchmark | Devstral Small 2505 | Gemini 4 Argon |
|---|---|---|
| LMArena Non-English | — | 1523 |
| LMArena Chinese | — | 1610 |
| LMArena Russian | — | 1537 |
| LMArena Spanish | — | 1497 |
Instruction Following Not comparable
Devstral Small 2505: —, Gemini 4 Argon: 80.1 (#2)
| Benchmark | Devstral Small 2505 | Gemini 4 Argon |
|---|---|---|
| LMArena Instruction Following | — | 1538 |
Long Context Not comparable
Devstral Small 2505: —, Gemini 4 Argon: 47.6 (#15)
| Benchmark | Devstral Small 2505 | Gemini 4 Argon |
|---|---|---|
| LMArena Longer Query | — | 1549 |
Writing & Preference Not comparable
Devstral Small 2505: —, Gemini 4 Argon: 71.4 (#19)
| Benchmark | Devstral Small 2505 | Gemini 4 Argon |
|---|---|---|
| LMArena Text | — | 1534 |
| LMArena Creative Writing | — | 1531 |
| LMArena Multi-Turn | — | 1557 |
Frequently asked questions
Is Devstral Small 2505 better than Gemini 4 Argon?
Gemini 4 Argon is the stronger model overall, scoring 56.5 to 34.3 on the Noometry Index.
Is Devstral Small 2505 or Gemini 4 Argon better for coding?
Gemini 4 Argon scores higher on coding benchmarks: 62.0 versus 38.9 in the Noometry coding category.
How many benchmarks do Devstral Small 2505 and Gemini 4 Argon share?
2 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Gemini 4 Argon has 21.