Model comparison
Mistral Small vs Muse Spark 1.2
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 33.4 on the Noometry Index. Mistral Small costs 7.6× less per token, which makes it the better buy when Muse Spark 1.2's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
Mistral AI
MetaSummary
- They share 19 benchmarks with published results for both. Mistral Small scores higher in 0 categories and Muse Spark 1.2 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.2 leads 51.3 to 19.8.
- The biggest single-benchmark swing is SciCode: 26.5% for Mistral Small and 56.4% for Muse Spark 1.2.
- Mistral Small is cheaper at $0.15 / $0.60 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 262K.
- Mistral Small has downloadable open weights; the other is API-only.
Side by side
| Mistral Small | Muse Spark 1.2 | |
|---|---|---|
| Provider | Mistral AI | Meta |
| Noometry Index | 33.4 | 50.3 |
| Released | 2024-02-26 | 2026-08-05 |
| Weights | Open | Proprietary |
| Context window | 262K | 1.05M |
| Max output | 256K | 131K |
| Input $ / M tokens | $0.15 | $1.25 |
| Output $ / M tokens | $0.60 | $4.25 |
| Results tracked | 39 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.2 leads
Mistral Small: 34.0 (#247), Muse Spark 1.2: 49.2 (#51)
| Benchmark | Mistral Small | Muse Spark 1.2 |
|---|---|---|
| SciCode | 26.5% | 56.4% |
| LMArena Coding | 1362 | 1495 |
| DeepSWE | — | 54.9% |
| LMArena WebDev | — | 1533 |
| FrontierSWE | — | 12% |
| WeirdML | — | 60.3% |
| BigCodeBench Instruct | 36.1% | — |
| LiveBench Coding | 36.2% | — |
| BigCodeBench Complete | 46.6% | — |
| ALE-Bench | 497.62 | — |
Agentic & Tool Use Muse Spark 1.2 leads
Mistral Small: 28.1 (#93), Muse Spark 1.2: 29.4 (#87)
| Benchmark | Mistral Small | Muse Spark 1.2 |
|---|---|---|
| APEX-Agents | — | 36.4% |
| Berkeley Function Calling Leaderboard | 37.1% | — |
| GDP.pdf | — | 16% |
Reasoning Muse Spark 1.2 leads
Mistral Small: 19.8 (#250), Muse Spark 1.2: 51.3 (#34)
| Benchmark | Mistral Small | Muse Spark 1.2 |
|---|---|---|
| CritPt | 0% | 17.7% |
| LMArena Hard Prompts | 1335 | 1486 |
| DTBench | 70.9% | 94.7% |
| LMCA | 20.6% | 48.4% |
| SimpleBench | — | 74.5% |
| Kagi LLM Benchmark | 37.8% | — |
| NYT Connections (extended) | — | 79.2% |
| LiveBench Reasoning | 44.8% | — |
| LiveBench Data Analysis | 53.7% | — |
| Epoch Capabilities Index | — | 154.87 |
| LiveBench | 44% | — |
Math Muse Spark 1.2 leads
Mistral Small: 16.4 (#293), Muse Spark 1.2: 46.4 (#70)
| Benchmark | Mistral Small | Muse Spark 1.2 |
|---|---|---|
| LMArena Math | 1341 | 1471 |
| OTIS Mock AIME 2024-2025 | 5.8% | — |
| ProofBench | — | 43% |
| LiveBench Math | 39.9% | — |
| MATH Level 5 | 46.8% | — |
Knowledge Muse Spark 1.2 leads
Mistral Small: 31.0 (#222), Muse Spark 1.2: 54.1 (#53)
| Benchmark | Mistral Small | Muse Spark 1.2 |
|---|---|---|
| LMArena Expert | 1291 | 1480 |
| GPQA Diamond | 47.5% | — |
| SimpleQA Verified | — | 60.3% |
| Vectara Hallucination Rate | 5.1% | — |
| MMLU | 68.7% | — |
Multimodal Muse Spark 1.2 leads
Mistral Small: 33.5 (#96), Muse Spark 1.2: 43.4 (#25)
| Benchmark | Mistral Small | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | 1142 | 1305 |
Multilingual Muse Spark 1.2 leads
Mistral Small: 45.5 (#169), Muse Spark 1.2: 57.1 (#11)
| Benchmark | Mistral Small | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | 1315 | 1478 |
| LMArena Chinese | 1340 | 1511 |
| LMArena French | 1337 | 1513 |
| LMArena Russian | 1324 | 1487 |
| LMArena Spanish | 1346 | 1498 |
| LMArena German | 1340 | — |
| LMArena Japanese | 1275 | — |
| LMArena Korean | 1259 | — |
Instruction Following Muse Spark 1.2 leads
Mistral Small: 66.4 (#209), Muse Spark 1.2: 76.7 (#36)
| Benchmark | Mistral Small | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | 1310 | 1461 |
| LiveBench Instruction Following | 63.7% | — |
Long Context Muse Spark 1.2 leads
Mistral Small: 40.4 (#156), Muse Spark 1.2: 45.2 (#48)
| Benchmark | Mistral Small | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | 1327 | 1475 |
Writing & Preference Muse Spark 1.2 leads
Mistral Small: 52.5 (#171), Muse Spark 1.2: 72.3 (#14)
| Benchmark | Mistral Small | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | 1338 | 1482 |
| LMArena Creative Writing | 1305 | 1449 |
| LMArena Multi-Turn | 1344 | 1494 |
| EQ-Bench Creative Writing | — | 1840 |
| LiveBench Language | 30.5% | — |
Frequently asked questions
Is Mistral Small better than Muse Spark 1.2?
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 33.4 on the Noometry Index. Mistral Small costs 7.6× 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, Mistral Small or Muse Spark 1.2?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Muse Spark 1.2 lists at $1.25 and $4.25.
Is Mistral Small or Muse Spark 1.2 better for coding?
Muse Spark 1.2 scores higher on coding benchmarks: 49.2 versus 34.0 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.2 does, with 1.05M tokens against 262K.
How many benchmarks do Mistral Small and Muse Spark 1.2 share?
19 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and Muse Spark 1.2 has 31.