Model comparison
Claude Sonnet 4.6 vs Devstral 2
Claude Sonnet 4.6 has enough public results to be ranked (#50); Devstral 2 does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
Mistral AISummary
- They share 1 benchmark with published results for both. Claude Sonnet 4.6 scores higher in 1 category and Devstral 2 in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where Claude Sonnet 4.6 leads 46.3 to 33.2.
- Devstral 2 is cheaper at $0.40 / $2 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.6.
- Claude Sonnet 4.6 accepts more context: 1M tokens versus 262K.
- Devstral 2 has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4.6 | Devstral 2 | |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 50.3 | 36.1 |
| Released | 2026-02-17 | 2025-12-09 |
| Weights | Proprietary | Open |
| Context window | 1M | 262K |
| Max output | 128K | 262K |
| Input $ / M tokens | $3 | $0.40 |
| Output $ / M tokens | $15 | $2 |
| Results tracked | 57 | 2 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 46.3 (#67), Devstral 2: 33.2 (#261)
| Benchmark | Claude Sonnet 4.6 | Devstral 2 |
|---|---|---|
| LMArena WebDev | 1522 | 1197 |
| SWE-bench Verified | 75.2% | — |
| DeepSWE | 29.9% | — |
| FrontierCode | 24.3% | — |
| SWE-bench Verified (bash only) | — | 53.8% |
| SciCode | 46.8% | — |
| WeirdML | 66.1% | — |
| LMArena Coding | 1504 | — |
| ALE-Bench | 1,327 | — |
Agentic & Tool Use Not comparable
Claude Sonnet 4.6: 39.1 (#28), Devstral 2: —
| Benchmark | Claude Sonnet 4.6 | Devstral 2 |
|---|---|---|
| Terminal-Bench | 53.4% | — |
| APEX-Agents | 43% | — |
| OSWorld 2.0 | 9.3% | — |
| DeepResearch Bench | 54.9% | — |
| OSWorld | 72.1% | — |
| ExploitBench | 23.6% | — |
| GBAEval | 48.8% | — |
| GDP.pdf | 18% | — |
| LMArena Search | 1221 | — |
| Vending-Bench 2 | 7,204 | — |
Reasoning Not comparable
Claude Sonnet 4.6: 46.1 (#45), Devstral 2: —
| Benchmark | Claude Sonnet 4.6 | Devstral 2 |
|---|---|---|
| ARC-AGI-2 | 60.4% | — |
| NYT Connections (extended) | 80.9% | — |
| ARC-AGI-1 | 86.5% | — |
| CritPt | 3.1% | — |
| Chess Puzzles | 13% | — |
| Thematic Generalization | 76.3% | — |
| LMArena Hard Prompts | 1484 | — |
| Mystery Game Puzzles | 16% | — |
| DTBench | 89.9% | — |
| LMCA | 46.5% | — |
| Epoch Capabilities Index | 152.24 | — |
| ForecastBench | 62 | — |
Math Not comparable
Claude Sonnet 4.6: 52.9 (#49), Devstral 2: —
| Benchmark | Claude Sonnet 4.6 | Devstral 2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 85.8% | — |
| ProofBench | 45% | — |
| LMArena Math | 1462 | — |
| FrontierMath (Feb 2025 set) | 32.4% | — |
| FrontierMath Tier 4 (v1) | 8.3% | — |
Knowledge Not comparable
Claude Sonnet 4.6: 51.7 (#65), Devstral 2: —
| Benchmark | Claude Sonnet 4.6 | Devstral 2 |
|---|---|---|
| GPQA Diamond | 87.4% | — |
| SimpleQA Verified | 35.5% | — |
| Vectara Hallucination Rate | 10.6% | — |
| LMArena Expert | 1500 | — |
Multimodal Not comparable
Claude Sonnet 4.6: 38.0 (#68), Devstral 2: —
| Benchmark | Claude Sonnet 4.6 | Devstral 2 |
|---|---|---|
| LMArena Vision | 1283 | — |
| Blueprint-Bench 2 | 6.7% | — |
| LMArena Document | 1482 | — |
Multilingual Not comparable
Claude Sonnet 4.6: 54.4 (#41), Devstral 2: —
| Benchmark | Claude Sonnet 4.6 | Devstral 2 |
|---|---|---|
| LMArena Non-English | 1440 | — |
| LMArena Chinese | 1491 | — |
| LMArena French | 1465 | — |
| LMArena German | 1428 | — |
| LMArena Japanese | 1420 | — |
| LMArena Korean | 1411 | — |
| LMArena Russian | 1440 | — |
| LMArena Spanish | 1464 | — |
Instruction Following Not comparable
Claude Sonnet 4.6: 77.4 (#25), Devstral 2: —
| Benchmark | Claude Sonnet 4.6 | Devstral 2 |
|---|---|---|
| LMArena Instruction Following | 1475 | — |
Long Context Not comparable
Claude Sonnet 4.6: 45.3 (#44), Devstral 2: —
| Benchmark | Claude Sonnet 4.6 | Devstral 2 |
|---|---|---|
| LMArena Longer Query | 1479 | — |
Writing & Preference Not comparable
Claude Sonnet 4.6: 70.2 (#22), Devstral 2: —
| Benchmark | Claude Sonnet 4.6 | Devstral 2 |
|---|---|---|
| LMArena Text | 1458 | — |
| LMArena Creative Writing | 1435 | — |
| EQ-Bench Creative Writing | 1810 | — |
| EQ-Bench 4 | 1207 | — |
| LMArena Multi-Turn | 1464 | — |
Frequently asked questions
Is Claude Sonnet 4.6 better than Devstral 2?
Claude Sonnet 4.6 has enough public results to be ranked (#50); Devstral 2 does not yet, so treat this comparison as directional.
Which is cheaper, Claude Sonnet 4.6 or Devstral 2?
Devstral 2 is cheaper. It lists at $0.40 per million input tokens and $2 per million output tokens; Claude Sonnet 4.6 lists at $3 and $15.
Is Claude Sonnet 4.6 or Devstral 2 better for coding?
Claude Sonnet 4.6 scores higher on coding benchmarks: 46.3 versus 33.2 in the Noometry coding category.
Which has the bigger context window?
Claude Sonnet 4.6 does, with 1M tokens against 262K.
How many benchmarks do Claude Sonnet 4.6 and Devstral 2 share?
1 benchmark has published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Devstral 2 has 2.