Model comparison
Magistral Small vs Muse Spark 1.2
Muse Spark 1.2 is the stronger model overall, scoring 49.8 to 29.9 on the Noometry Index. Magistral Small costs 2.7× less per token, which makes it the better buy when Muse Spark 1.2's lead doesn't matter for your workload.
Last verified . 4 shared benchmarks.
Mistral AI
MetaSummary
- They share 4 benchmarks with published results for both. Magistral Small scores higher in 0 categories and Muse Spark 1.2 in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.2 leads 50.4 to 6.9.
- The biggest single-benchmark swing is DTBench: 61.3% for Magistral Small and 94.7% for Muse Spark 1.2.
- Magistral Small is cheaper at $0.50 / $1.50 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.2.
- Muse Spark 1.2 accepts more context: 1.05M tokens versus 128K.
- Magistral Small has downloadable open weights; the other is API-only.
Side by side
| Magistral Small | Muse Spark 1.2 | |
|---|---|---|
| Provider | Mistral AI | Meta |
| Noometry Index | 29.9 | 49.8 |
| Released | 2025-06-10 | 2026-08-05 |
| Weights | Open | Proprietary |
| Context window | 128K | 1.05M |
| Max output | 40K | 131K |
| Input $ / M tokens | $0.50 | $1.25 |
| Output $ / M tokens | $1.50 | $4.25 |
| Results tracked | 10 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.2 leads
Magistral Small: 37.8 (#172), Muse Spark 1.2: 48.6 (#49)
| Benchmark | Magistral Small | Muse Spark 1.2 |
|---|---|---|
| SciCode | 35.2% | 56.4% |
| DeepSWE | — | 54.9% |
| LMArena WebDev | — | 1532 |
| FrontierSWE | — | 12% |
| WeirdML | — | 60.3% |
| LMArena Coding | — | 1497 |
Agentic & Tool Use Not comparable
Magistral Small: —, Muse Spark 1.2: 29.5 (#77)
| Benchmark | Magistral Small | Muse Spark 1.2 |
|---|---|---|
| APEX-Agents | — | 36.4% |
| GDP.pdf | — | 16% |
Reasoning Muse Spark 1.2 leads
Magistral Small: 6.9 (#345), Muse Spark 1.2: 50.4 (#32)
| Benchmark | Magistral Small | Muse Spark 1.2 |
|---|---|---|
| CritPt | 0.3% | 17.7% |
| DTBench | 61.3% | 94.7% |
| Epoch Capabilities Index | 133.19 | 155.18 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | — | 74.5% |
| Kagi LLM Benchmark | 6.3% | — |
| NYT Connections (extended) | — | 79.2% |
| ARC-AGI-1 | 5% | — |
| Chess Puzzles | 3% | — |
| LMArena Hard Prompts | — | 1490 |
| LMCA | — | 48.4% |
Math Muse Spark 1.2 leads
Magistral Small: 24.9 (#253), Muse Spark 1.2: 43.8 (#68)
| Benchmark | Magistral Small | Muse Spark 1.2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 30% | — |
| ProofBench | — | 43% |
Knowledge Muse Spark 1.2 leads
Magistral Small: 30.9 (#215), Muse Spark 1.2: 53.9 (#49)
| Benchmark | Magistral Small | Muse Spark 1.2 |
|---|---|---|
| GPQA Diamond | 56.1% | — |
| SimpleQA Verified | — | 60.3% |
| LMArena Expert | — | 1485 |
Multimodal Not comparable
Magistral Small: —, Muse Spark 1.2: 42.6 (#24)
| Benchmark | Magistral Small | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | — | 1304 |
Multilingual Not comparable
Magistral Small: —, Muse Spark 1.2: 57.4 (#10)
| Benchmark | Magistral Small | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | — | 1479 |
| LMArena Chinese | — | 1519 |
| LMArena Russian | — | 1494 |
Instruction Following Not comparable
Magistral Small: —, Muse Spark 1.2: 77.1 (#30)
| Benchmark | Magistral Small | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | — | 1466 |
Long Context Not comparable
Magistral Small: —, Muse Spark 1.2: 45.4 (#35)
| Benchmark | Magistral Small | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | — | 1483 |
Writing & Preference Not comparable
Magistral Small: —, Muse Spark 1.2: 72.6 (#14)
| Benchmark | Magistral Small | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | — | 1486 |
| LMArena Creative Writing | — | 1444 |
| EQ-Bench Creative Writing | — | 1840 |
| LMArena Multi-Turn | — | 1504 |
Frequently asked questions
Is Magistral Small better than Muse Spark 1.2?
Muse Spark 1.2 is the stronger model overall, scoring 49.8 to 29.9 on the Noometry Index. Magistral Small costs 2.7× less per token, which makes it the better buy when Muse Spark 1.2's lead doesn't matter for your workload.
Which is cheaper, Magistral Small or Muse Spark 1.2?
Magistral Small is cheaper. It lists at $0.50 per million input tokens and $1.50 per million output tokens; Muse Spark 1.2 lists at $1.25 and $4.25.
Is Magistral Small or Muse Spark 1.2 better for coding?
Muse Spark 1.2 scores higher on coding benchmarks: 48.6 versus 37.8 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.2 does, with 1.05M tokens against 128K.
How many benchmarks do Magistral Small and Muse Spark 1.2 share?
4 benchmarks have published results for both models. Magistral Small has 10 scored results on Noometry and Muse Spark 1.2 has 28.