Model comparison
Mistral Large 3 vs Muse Spark 1.2
Muse Spark 1.2 is the stronger model overall, scoring 49.8 to 38.6 on the Noometry Index. Mistral Large 3 costs 5.3× 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 Large 3 scores higher in 0 categories and Muse Spark 1.2 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.2 leads 50.4 to 14.6.
- The biggest single-benchmark swing is NYT Connections (extended): 7.5% for Mistral Large 3 and 79.2% for Muse Spark 1.2.
- Mistral Large 3 is cheaper at $0.25 / $0.75 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 Large 3 has downloadable open weights; the other is API-only.
Side by side
| Mistral Large 3 | Muse Spark 1.2 | |
|---|---|---|
| Provider | Mistral AI | Meta |
| Noometry Index | 38.6 | 49.8 |
| Released | 2025-12-02 | 2026-08-05 |
| Weights | Open | Proprietary |
| Context window | 262K | 1.05M |
| Max output | 8K | 131K |
| Input $ / M tokens | $0.25 | $1.25 |
| Output $ / M tokens | $0.75 | $4.25 |
| Results tracked | 24 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.2 leads
Mistral Large 3: 34.1 (#230), Muse Spark 1.2: 48.6 (#49)
| Benchmark | Mistral Large 3 | Muse Spark 1.2 |
|---|---|---|
| LMArena WebDev | 1230 | 1532 |
| LMArena Coding | 1447 | 1497 |
| DeepSWE | — | 54.9% |
| FrontierSWE | — | 12% |
| SciCode | — | 56.4% |
| WeirdML | — | 60.3% |
Agentic & Tool Use Not comparable
Mistral Large 3: —, Muse Spark 1.2: 29.5 (#77)
| Benchmark | Mistral Large 3 | Muse Spark 1.2 |
|---|---|---|
| APEX-Agents | — | 36.4% |
| GDP.pdf | — | 16% |
Reasoning Muse Spark 1.2 leads
Mistral Large 3: 14.6 (#314), Muse Spark 1.2: 50.4 (#32)
| Benchmark | Mistral Large 3 | Muse Spark 1.2 |
|---|---|---|
| NYT Connections (extended) | 7.5% | 79.2% |
| LMArena Hard Prompts | 1429 | 1490 |
| SimpleBench | — | 74.5% |
| Kagi LLM Benchmark | 50.9% | — |
| CritPt | — | 17.7% |
| Thematic Generalization | 23% | — |
| DTBench | — | 94.7% |
| LMCA | — | 48.4% |
| Epoch Capabilities Index | — | 155.18 |
Math Muse Spark 1.2 leads
Mistral Large 3: 36.0 (#131), Muse Spark 1.2: 43.8 (#68)
| Benchmark | Mistral Large 3 | Muse Spark 1.2 |
|---|---|---|
| ProofBench | — | 43% |
| LMArena Math | 1415 | — |
Knowledge Muse Spark 1.2 leads
Mistral Large 3: 35.5 (#173), Muse Spark 1.2: 53.9 (#49)
| Benchmark | Mistral Large 3 | Muse Spark 1.2 |
|---|---|---|
| LMArena Expert | 1421 | 1485 |
| SimpleQA Verified | — | 60.3% |
| Vectara Hallucination Rate | 14.5% | — |
Multimodal Muse Spark 1.2 leads
Mistral Large 3: 37.6 (#65), Muse Spark 1.2: 42.6 (#24)
| Benchmark | Mistral Large 3 | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | 1222 | 1304 |
Multilingual Muse Spark 1.2 leads
Mistral Large 3: 52.6 (#79), Muse Spark 1.2: 57.4 (#10)
| Benchmark | Mistral Large 3 | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | 1412 | 1479 |
| LMArena Chinese | 1448 | 1519 |
| LMArena Russian | 1412 | 1494 |
| LMArena French | 1456 | — |
| LMArena German | 1438 | — |
| LMArena Japanese | 1399 | — |
| LMArena Korean | 1384 | — |
| LMArena Spanish | 1437 | — |
Instruction Following Muse Spark 1.2 leads
Mistral Large 3: 74.1 (#104), Muse Spark 1.2: 77.1 (#30)
| Benchmark | Mistral Large 3 | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | 1402 | 1466 |
Long Context Muse Spark 1.2 leads
Mistral Large 3: 43.1 (#102), Muse Spark 1.2: 45.4 (#35)
| Benchmark | Mistral Large 3 | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | 1413 | 1483 |
Writing & Preference Muse Spark 1.2 leads
Mistral Large 3: 60.2 (#100), Muse Spark 1.2: 72.6 (#14)
| Benchmark | Mistral Large 3 | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | 1427 | 1486 |
| LMArena Creative Writing | 1385 | 1444 |
| EQ-Bench Creative Writing | 1412 | 1840 |
| LMArena Multi-Turn | 1429 | 1504 |
Frequently asked questions
Is Mistral Large 3 better than Muse Spark 1.2?
Muse Spark 1.2 is the stronger model overall, scoring 49.8 to 38.6 on the Noometry Index. Mistral Large 3 costs 5.3× 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 Large 3 or Muse Spark 1.2?
Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Muse Spark 1.2 lists at $1.25 and $4.25.
Is Mistral Large 3 or Muse Spark 1.2 better for coding?
Muse Spark 1.2 scores higher on coding benchmarks: 48.6 versus 34.1 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 Large 3 and Muse Spark 1.2 share?
15 benchmarks have published results for both models. Mistral Large 3 has 24 scored results on Noometry and Muse Spark 1.2 has 28.