Model comparison
Devstral Small 2505 vs Muse Spark 1.3
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 34.3 on the Noometry Index. Devstral Small 2505 costs 13× less per token, which makes it the better buy when Muse Spark 1.3's lead doesn't matter for your workload.
Last verified . 2 shared benchmarks.
Mistral AI
MetaSummary
- They share 2 benchmarks with published results for both. Devstral Small 2505 scores higher in 0 categories and Muse Spark 1.3 in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.3 leads 54.0 to 19.7.
- The biggest single-benchmark swing is SciCode: 28.8% for Devstral Small 2505 and 59.7% for Muse Spark 1.3.
- Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.3.
- Muse Spark 1.3 accepts more context: 1.05M tokens versus 128K.
- Devstral Small 2505 has downloadable open weights; the other is API-only.
Side by side
| Devstral Small 2505 | Muse Spark 1.3 | |
|---|---|---|
| Provider | Mistral AI | Meta |
| Noometry Index | 34.3 | 54.8 |
| Released | 2025-05-07 | 2026-09-02 |
| Weights | Open | Proprietary |
| Context window | 128K | 1.05M |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.10 | $1.25 |
| Output $ / M tokens | $0.30 | $4.25 |
| Results tracked | 4 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.3 leads
Devstral Small 2505: 38.9 (#166), Muse Spark 1.3: 56.6 (#21)
| Benchmark | Devstral Small 2505 | Muse Spark 1.3 |
|---|---|---|
| SciCode | 28.8% | 59.7% |
| SWE-bench Verified (bash only) | 56.4% | — |
| CursorBench | — | 41.6% |
| LMArena WebDev | — | 1657 |
| LMArena Coding | — | 1514 |
Agentic & Tool Use Not comparable
Devstral Small 2505: —, Muse Spark 1.3: 38.6 (#30)
| Benchmark | Devstral Small 2505 | Muse Spark 1.3 |
|---|---|---|
| APEX-Agents | — | 57.8% |
| GDP.pdf | — | 27.6% |
Reasoning Muse Spark 1.3 leads
Devstral Small 2505: 19.7 (#252), Muse Spark 1.3: 54.0 (#27)
| Benchmark | Devstral Small 2505 | Muse Spark 1.3 |
|---|---|---|
| CritPt | 0% | 26% |
| Kagi LLM Benchmark | 37.7% | — |
| NYT Connections (extended) | — | 85.1% |
| Chess Puzzles | — | 38% |
| LMArena Hard Prompts | — | 1503 |
| Mystery Game Puzzles | — | 25% |
| DTBench | — | 96.5% |
| LMCA | — | 53.9% |
| Bench to the Future 3 | — | 0.14 |
| Epoch Capabilities Index | — | 156.75 |
Math Not comparable
Devstral Small 2505: —, Muse Spark 1.3: 73.1 (#21)
| Benchmark | Devstral Small 2505 | Muse Spark 1.3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 74.4% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 99.2% |
| ProofBench | — | 58% |
| LMArena Math | — | 1494 |
Knowledge Not comparable
Devstral Small 2505: —, Muse Spark 1.3: 42.6 (#95)
| Benchmark | Devstral Small 2505 | Muse Spark 1.3 |
|---|---|---|
| LMArena Expert | — | 1516 |
Multimodal Not comparable
Devstral Small 2505: —, Muse Spark 1.3: 43.7 (#22)
| Benchmark | Devstral Small 2505 | Muse Spark 1.3 |
|---|---|---|
| LMArena Vision | — | 1309 |
| LMArena Document | — | 1471 |
Multilingual Not comparable
Devstral Small 2505: —, Muse Spark 1.3: 57.4 (#8)
| Benchmark | Devstral Small 2505 | Muse Spark 1.3 |
|---|---|---|
| LMArena Non-English | — | 1481 |
| LMArena Chinese | — | 1529 |
| LMArena French | — | 1524 |
| LMArena German | — | 1515 |
| LMArena Japanese | — | 1474 |
| LMArena Korean | — | 1501 |
| LMArena Russian | — | 1490 |
| LMArena Spanish | — | 1490 |
Instruction Following Not comparable
Devstral Small 2505: —, Muse Spark 1.3: 77.5 (#22)
| Benchmark | Devstral Small 2505 | Muse Spark 1.3 |
|---|---|---|
| LMArena Instruction Following | — | 1477 |
Long Context Not comparable
Devstral Small 2505: —, Muse Spark 1.3: 45.6 (#32)
| Benchmark | Devstral Small 2505 | Muse Spark 1.3 |
|---|---|---|
| LMArena Longer Query | — | 1488 |
Writing & Preference Not comparable
Devstral Small 2505: —, Muse Spark 1.3: 73.6 (#9)
| Benchmark | Devstral Small 2505 | Muse Spark 1.3 |
|---|---|---|
| LMArena Text | — | 1490 |
| LMArena Creative Writing | — | 1455 |
| EQ-Bench Creative Writing | — | 1906 |
| LMArena Multi-Turn | — | 1482 |
Frequently asked questions
Is Devstral Small 2505 better than Muse Spark 1.3?
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 34.3 on the Noometry Index. Devstral Small 2505 costs 13× less per token, which makes it the better buy when Muse Spark 1.3's lead doesn't matter for your workload.
Which is cheaper, Devstral Small 2505 or Muse Spark 1.3?
Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Muse Spark 1.3 lists at $1.25 and $4.25.
Is Devstral Small 2505 or Muse Spark 1.3 better for coding?
Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 38.9 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.3 does, with 1.05M tokens against 128K.
How many benchmarks do Devstral Small 2505 and Muse Spark 1.3 share?
2 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Muse Spark 1.3 has 37.