Model comparison
Devstral 2 vs Muse Spark
Muse Spark has enough public results to be ranked (#46); Devstral 2 does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Mistral AI
MetaSummary
- The widest gap is in coding, where Muse Spark leads 46.2 to 33.2.
- Devstral 2 has downloadable open weights; the other is API-only.
Side by side
| Devstral 2 | Muse Spark | |
|---|---|---|
| Provider | Mistral AI | Meta |
| Noometry Index | 36.1 | 50.6 |
| Released | 2025-12-09 | 2026-04-08 |
| Weights | Open | Proprietary |
| Context window | 262K | — |
| Max output | 262K | — |
| Input $ / M tokens | $0.40 | — |
| Output $ / M tokens | $2 | — |
| Results tracked | 2 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark leads
Devstral 2: 33.2 (#261), Muse Spark: 46.2 (#69)
| Benchmark | Devstral 2 | Muse Spark |
|---|---|---|
| SWE-bench Verified (bash only) | 53.8% | — |
| LMArena WebDev | 1197 | — |
| SciCode | — | 51.5% |
| LMArena Coding | — | 1481 |
Reasoning Not comparable
Devstral 2: —, Muse Spark: 35.9 (#67)
| Benchmark | Devstral 2 | Muse Spark |
|---|---|---|
| CritPt | — | 11.3% |
| LMArena Hard Prompts | — | 1474 |
| Epoch Capabilities Index | — | 152.04 |
Math Not comparable
Devstral 2: —, Muse Spark: 47.8 (#66)
| Benchmark | Devstral 2 | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 17% |
| LMArena Math | — | 1455 |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Not comparable
Devstral 2: —, Muse Spark: 65.7 (#13)
| Benchmark | Devstral 2 | Muse Spark |
|---|---|---|
| GPQA Diamond | — | 89.8% |
| Humanity's Last Exam | — | 40.6% |
| LMArena Expert | — | 1457 |
Multimodal Not comparable
Devstral 2: —, Muse Spark: 43.4 (#24)
| Benchmark | Devstral 2 | Muse Spark |
|---|---|---|
| LMArena Vision | — | 1306 |
| LMArena Document | — | 1444 |
Multilingual Not comparable
Devstral 2: —, Muse Spark: 56.1 (#24)
| Benchmark | Devstral 2 | Muse Spark |
|---|---|---|
| LMArena Non-English | — | 1464 |
| LMArena Chinese | — | 1509 |
| LMArena French | — | 1497 |
| LMArena German | — | 1497 |
| LMArena Korean | — | 1459 |
| LMArena Russian | — | 1466 |
| LMArena Spanish | — | 1472 |
Instruction Following Not comparable
Devstral 2: —, Muse Spark: 75.9 (#51)
| Benchmark | Devstral 2 | Muse Spark |
|---|---|---|
| LMArena Instruction Following | — | 1442 |
Long Context Not comparable
Devstral 2: —, Muse Spark: 44.4 (#69)
| Benchmark | Devstral 2 | Muse Spark |
|---|---|---|
| LMArena Longer Query | — | 1451 |
Writing & Preference Not comparable
Devstral 2: —, Muse Spark: 66.0 (#39)
| Benchmark | Devstral 2 | Muse Spark |
|---|---|---|
| LMArena Text | — | 1474 |
| LMArena Creative Writing | — | 1459 |
| LMArena Multi-Turn | — | 1477 |
Frequently asked questions
Is Devstral 2 better than Muse Spark?
Muse Spark has enough public results to be ranked (#46); Devstral 2 does not yet, so treat this comparison as directional.
Is Devstral 2 or Muse Spark better for coding?
Muse Spark scores higher on coding benchmarks: 46.2 versus 33.2 in the Noometry coding category.
How many benchmarks do Devstral 2 and Muse Spark share?
0 benchmarks have published results for both models. Devstral 2 has 2 scored results on Noometry and Muse Spark has 27.