Model comparison
Mistral Small 3 vs Muse Spark 1.2
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 31.2 on the Noometry Index. Mistral Small 3 costs 35× less per token, which makes it the better buy when Muse Spark 1.2's lead doesn't matter for your workload.
Last verified . 15 shared benchmarks.
Mistral AI
MetaSummary
- They share 15 benchmarks with published results for both. Mistral Small 3 scores higher in 0 categories and Muse Spark 1.2 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Muse Spark 1.2 leads 72.3 to 32.2.
- Mistral Small 3 is cheaper at $0.05 / $0.08 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 33K.
- Mistral Small 3 has downloadable open weights; the other is API-only.
Side by side
| Mistral Small 3 | Muse Spark 1.2 | |
|---|---|---|
| Provider | Mistral AI | Meta |
| Noometry Index | 31.2 | 50.3 |
| Released | 2025-01-30 | 2026-08-05 |
| Weights | Open | Proprietary |
| Context window | 33K | 1.05M |
| Max output | 16K | 131K |
| Input $ / M tokens | $0.05 | $1.25 |
| Output $ / M tokens | $0.08 | $4.25 |
| Results tracked | 24 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.2 leads
Mistral Small 3: 36.5 (#207), Muse Spark 1.2: 49.2 (#51)
| Benchmark | Mistral Small 3 | Muse Spark 1.2 |
|---|---|---|
| LMArena Coding | 1246 | 1495 |
| DeepSWE | — | 54.9% |
| LMArena WebDev | — | 1533 |
| FrontierSWE | — | 12% |
| SciCode | — | 56.4% |
| WeirdML | — | 60.3% |
| BigCodeBench Instruct | 45.3% | — |
| BigCodeBench Complete | 50.4% | — |
Agentic & Tool Use Not comparable
Mistral Small 3: —, Muse Spark 1.2: 29.4 (#87)
| Benchmark | Mistral Small 3 | Muse Spark 1.2 |
|---|---|---|
| APEX-Agents | — | 36.4% |
| GDP.pdf | — | 16% |
Reasoning Muse Spark 1.2 leads
Mistral Small 3: 18.9 (#273), Muse Spark 1.2: 51.3 (#34)
| Benchmark | Mistral Small 3 | Muse Spark 1.2 |
|---|---|---|
| LMArena Hard Prompts | 1233 | 1486 |
| Epoch Capabilities Index | 127.07 | 154.87 |
| SimpleBench | — | 74.5% |
| NYT Connections (extended) | — | 79.2% |
| CritPt | — | 17.7% |
| Chess Puzzles | 0% | — |
| DTBench | — | 94.7% |
| LMCA | — | 48.4% |
Math Muse Spark 1.2 leads
Mistral Small 3: 16.3 (#295), Muse Spark 1.2: 46.4 (#70)
| Benchmark | Mistral Small 3 | Muse Spark 1.2 |
|---|---|---|
| LMArena Math | 1240 | 1471 |
| OTIS Mock AIME 2024-2025 | 6.7% | — |
| ProofBench | — | 43% |
Knowledge Muse Spark 1.2 leads
Mistral Small 3: 25.1 (#263), Muse Spark 1.2: 54.1 (#53)
| Benchmark | Mistral Small 3 | Muse Spark 1.2 |
|---|---|---|
| LMArena Expert | 1202 | 1480 |
| GPQA Diamond | 47.3% | — |
| SimpleQA Verified | — | 60.3% |
| Confabulations | 25.2% | — |
Multimodal Not comparable
Mistral Small 3: —, Muse Spark 1.2: 43.4 (#25)
| Benchmark | Mistral Small 3 | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | — | 1305 |
Multilingual Muse Spark 1.2 leads
Mistral Small 3: 37.3 (#236), Muse Spark 1.2: 57.1 (#11)
| Benchmark | Mistral Small 3 | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | 1198 | 1478 |
| LMArena Chinese | 1204 | 1511 |
| LMArena French | 1203 | 1513 |
| LMArena Russian | 1216 | 1487 |
| LMArena German | 1211 | — |
| LMArena Japanese | 1111 | — |
| LMArena Korean | 1188 | — |
| LMArena Spanish | — | 1498 |
Instruction Following Muse Spark 1.2 leads
Mistral Small 3: 63.7 (#229), Muse Spark 1.2: 76.7 (#36)
| Benchmark | Mistral Small 3 | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | 1214 | 1461 |
Long Context Muse Spark 1.2 leads
Mistral Small 3: 37.8 (#211), Muse Spark 1.2: 45.2 (#48)
| Benchmark | Mistral Small 3 | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | 1246 | 1475 |
Writing & Preference Muse Spark 1.2 leads
Mistral Small 3: 32.2 (#280), Muse Spark 1.2: 72.3 (#14)
| Benchmark | Mistral Small 3 | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | 1234 | 1482 |
| LMArena Creative Writing | 1195 | 1449 |
| EQ-Bench Creative Writing | 707 | 1840 |
| LMArena Multi-Turn | 1217 | 1494 |
Frequently asked questions
Is Mistral Small 3 better than Muse Spark 1.2?
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 31.2 on the Noometry Index. Mistral Small 3 costs 35× 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 3 or Muse Spark 1.2?
Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Muse Spark 1.2 lists at $1.25 and $4.25.
Is Mistral Small 3 or Muse Spark 1.2 better for coding?
Muse Spark 1.2 scores higher on coding benchmarks: 49.2 versus 36.5 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.2 does, with 1.05M tokens against 33K.
How many benchmarks do Mistral Small 3 and Muse Spark 1.2 share?
15 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Muse Spark 1.2 has 31.