Model comparison
Mistral Large vs Muse Spark 1.2
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 31.9 on the Noometry Index.
Last verified . 21 shared benchmarks.
Mistral AI
MetaSummary
- They share 21 benchmarks with published results for both. Mistral Large scores higher in 0 categories and Muse Spark 1.2 in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.2 leads 51.3 to 15.8.
- The biggest single-benchmark swing is SimpleBench: 22.5% for Mistral Large and 74.5% for Muse Spark 1.2.
- Muse Spark 1.2 is cheaper at $1.25 / $4.25 per million input/output tokens, against $2 / $6 for Mistral Large.
- Muse Spark 1.2 accepts more context: 1.05M tokens versus 131K.
- Mistral Large has downloadable open weights; the other is API-only.
Side by side
| Mistral Large | Muse Spark 1.2 | |
|---|---|---|
| Provider | Mistral AI | Meta |
| Noometry Index | 31.9 | 50.3 |
| Released | 2024-02-26 | 2026-08-05 |
| Weights | Open | Proprietary |
| Context window | 131K | 1.05M |
| Max output | 16K | 131K |
| Input $ / M tokens | $2 | $1.25 |
| Output $ / M tokens | $6 | $4.25 |
| Results tracked | 51 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.2 leads
Mistral Large: 34.3 (#240), Muse Spark 1.2: 49.2 (#51)
| Benchmark | Mistral Large | Muse Spark 1.2 |
|---|---|---|
| SciCode | 36.2% | 56.4% |
| LMArena Coding | 1277 | 1495 |
| DeepSWE | — | 54.9% |
| LMArena WebDev | — | 1533 |
| FrontierSWE | — | 12% |
| WeirdML | — | 60.3% |
| BigCodeBench Instruct | 30% | — |
| LiveBench Coding | 47.1% | — |
| BigCodeBench Complete | 38.3% | — |
| ALE-Bench | 264.7 | — |
| HumanEval+ | 62.2% | — |
| MBPP+ | 59.5% | — |
Agentic & Tool Use Too close to call
Mistral Large: 28.6 (#89), Muse Spark 1.2: 29.4 (#87)
| Benchmark | Mistral Large | Muse Spark 1.2 |
|---|---|---|
| APEX-Agents | — | 36.4% |
| Berkeley Function Calling Leaderboard | 38.4% | — |
| GDP.pdf | — | 16% |
Reasoning Muse Spark 1.2 leads
Mistral Large: 15.8 (#310), Muse Spark 1.2: 51.3 (#34)
| Benchmark | Mistral Large | Muse Spark 1.2 |
|---|---|---|
| SimpleBench | 22.5% | 74.5% |
| CritPt | 0% | 17.7% |
| LMArena Hard Prompts | 1257 | 1486 |
| DTBench | 65.1% | 94.7% |
| LMCA | 16.7% | 48.4% |
| Epoch Capabilities Index | 128.52 | 154.87 |
| NYT Connections (extended) | — | 79.2% |
| LiveBench Reasoning | 43.5% | — |
| LiveBench Data Analysis | 50.1% | — |
| ForecastBench | 57.1 | — |
| LiveBench | 48.4% | — |
Math Muse Spark 1.2 leads
Mistral Large: 18.2 (#291), Muse Spark 1.2: 46.4 (#70)
| Benchmark | Mistral Large | Muse Spark 1.2 |
|---|---|---|
| LMArena Math | 1262 | 1471 |
| OTIS Mock AIME 2024-2025 | 8.5% | — |
| ProofBench | — | 43% |
| Omni-MATH | 28.1% | — |
| LiveBench Math | 42.5% | — |
| MATH Level 5 | 50.3% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Muse Spark 1.2 leads
Mistral Large: 30.1 (#230), Muse Spark 1.2: 54.1 (#53)
| Benchmark | Mistral Large | Muse Spark 1.2 |
|---|---|---|
| LMArena Expert | 1232 | 1480 |
| GPQA Diamond | 51.3% | — |
| SimpleQA Verified | — | 60.3% |
| MMLU-Pro | 59.9% | — |
| Confabulations | 21.4% | — |
| Vectara Hallucination Rate | 4.5% | — |
| GPQA (HELM) | 43.5% | — |
| MMLU | 80% | — |
Multimodal Not comparable
Mistral Large: —, Muse Spark 1.2: 43.4 (#25)
| Benchmark | Mistral Large | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | — | 1305 |
Multilingual Muse Spark 1.2 leads
Mistral Large: 40.0 (#219), Muse Spark 1.2: 57.1 (#11)
| Benchmark | Mistral Large | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | 1237 | 1478 |
| LMArena Chinese | 1240 | 1511 |
| LMArena French | 1325 | 1513 |
| LMArena Russian | 1257 | 1487 |
| LMArena Spanish | 1268 | 1498 |
| LMArena German | 1254 | — |
| LMArena Japanese | 1188 | — |
| LMArena Korean | 1202 | — |
Instruction Following Muse Spark 1.2 leads
Mistral Large: 67.9 (#191), Muse Spark 1.2: 76.7 (#36)
| Benchmark | Mistral Large | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | 1249 | 1461 |
| LiveBench Instruction Following | 67.9% | — |
| IFEval | 87.7% | — |
Long Context Muse Spark 1.2 leads
Mistral Large: 38.3 (#199), Muse Spark 1.2: 45.2 (#48)
| Benchmark | Mistral Large | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | 1261 | 1475 |
Writing & Preference Muse Spark 1.2 leads
Mistral Large: 40.7 (#242), Muse Spark 1.2: 72.3 (#14)
| Benchmark | Mistral Large | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | 1266 | 1482 |
| LMArena Creative Writing | 1243 | 1449 |
| EQ-Bench Creative Writing | 985 | 1840 |
| LMArena Multi-Turn | 1260 | 1494 |
| Short-Story Creative Writing | 69% | — |
| WildBench | 80.1% | — |
| LiveBench Language | 39.4% | — |
Frequently asked questions
Is Mistral Large better than Muse Spark 1.2?
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 31.9 on the Noometry Index.
Which is cheaper, Mistral Large or Muse Spark 1.2?
Muse Spark 1.2 is cheaper. It lists at $1.25 per million input tokens and $4.25 per million output tokens; Mistral Large lists at $2 and $6.
Is Mistral Large or Muse Spark 1.2 better for coding?
Muse Spark 1.2 scores higher on coding benchmarks: 49.2 versus 34.3 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.2 does, with 1.05M tokens against 131K.
How many benchmarks do Mistral Large and Muse Spark 1.2 share?
21 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and Muse Spark 1.2 has 31.