Model comparison
Ministral 8B vs Muse Spark 1.2
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 28.2 on the Noometry Index. Ministral 8B costs 13× less per token, which makes it the better buy when Muse Spark 1.2's lead doesn't matter for your workload.
Last verified . 13 shared benchmarks.
Mistral AI
MetaSummary
- They share 13 benchmarks with published results for both. Ministral 8B 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 knowledge, where Muse Spark 1.2 leads 54.1 to 12.6.
- The biggest single-benchmark swing is DTBench: 45.7% for Ministral 8B and 94.7% for Muse Spark 1.2.
- Ministral 8B is cheaper at $0.15 / $0.15 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.
- Ministral 8B has downloadable open weights; the other is API-only.
Side by side
| Ministral 8B | Muse Spark 1.2 | |
|---|---|---|
| Provider | Mistral AI | Meta |
| Noometry Index | 28.2 | 50.3 |
| Released | 2024-10-01 | 2026-08-05 |
| Weights | Open | Proprietary |
| Context window | 262K | 1.05M |
| Max output | 262K | 131K |
| Input $ / M tokens | $0.15 | $1.25 |
| Output $ / M tokens | $0.15 | $4.25 |
| Results tracked | 17 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.2 leads
Ministral 8B: 35.0 (#230), Muse Spark 1.2: 49.2 (#51)
| Benchmark | Ministral 8B | Muse Spark 1.2 |
|---|---|---|
| LMArena Coding | 1202 | 1495 |
| DeepSWE | — | 54.9% |
| LMArena WebDev | — | 1533 |
| FrontierSWE | — | 12% |
| SciCode | — | 56.4% |
| WeirdML | — | 60.3% |
Agentic & Tool Use Muse Spark 1.2 leads
Ministral 8B: 16.4 (#148), Muse Spark 1.2: 29.4 (#87)
| Benchmark | Ministral 8B | Muse Spark 1.2 |
|---|---|---|
| APEX-Agents | — | 36.4% |
| Berkeley Function Calling Leaderboard | 11.1% | — |
| GDP.pdf | — | 16% |
Reasoning Muse Spark 1.2 leads
Ministral 8B: 18.4 (#281), Muse Spark 1.2: 51.3 (#34)
| Benchmark | Ministral 8B | Muse Spark 1.2 |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1486 |
| DTBench | 45.7% | 94.7% |
| SimpleBench | — | 74.5% |
| NYT Connections (extended) | — | 79.2% |
| CritPt | — | 17.7% |
| LMCA | — | 48.4% |
| Epoch Capabilities Index | — | 154.87 |
Math Muse Spark 1.2 leads
Ministral 8B: 25.7 (#267), Muse Spark 1.2: 46.4 (#70)
| Benchmark | Ministral 8B | Muse Spark 1.2 |
|---|---|---|
| LMArena Math | 1188 | 1471 |
| ProofBench | — | 43% |
| MATH Level 5 | 14.9% | — |
Knowledge Muse Spark 1.2 leads
Ministral 8B: 12.6 (#297), Muse Spark 1.2: 54.1 (#53)
| Benchmark | Ministral 8B | Muse Spark 1.2 |
|---|---|---|
| LMArena Expert | 1170 | 1480 |
| GPQA Diamond | 27.1% | — |
| SimpleQA Verified | — | 60.3% |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Not comparable
Ministral 8B: —, Muse Spark 1.2: 43.4 (#25)
| Benchmark | Ministral 8B | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | — | 1305 |
Multilingual Muse Spark 1.2 leads
Ministral 8B: 35.1 (#247), Muse Spark 1.2: 57.1 (#11)
| Benchmark | Ministral 8B | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | 1165 | 1478 |
| LMArena Chinese | 1193 | 1511 |
| LMArena Russian | 1195 | 1487 |
| LMArena French | — | 1513 |
| LMArena Spanish | — | 1498 |
Instruction Following Muse Spark 1.2 leads
Ministral 8B: 60.5 (#250), Muse Spark 1.2: 76.7 (#36)
| Benchmark | Ministral 8B | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | 1161 | 1461 |
Long Context Muse Spark 1.2 leads
Ministral 8B: 36.7 (#227), Muse Spark 1.2: 45.2 (#48)
| Benchmark | Ministral 8B | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | 1212 | 1475 |
Writing & Preference Muse Spark 1.2 leads
Ministral 8B: 39.6 (#246), Muse Spark 1.2: 72.3 (#14)
| Benchmark | Ministral 8B | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | 1191 | 1482 |
| LMArena Creative Writing | 1175 | 1449 |
| LMArena Multi-Turn | 1166 | 1494 |
| EQ-Bench Creative Writing | — | 1840 |
Frequently asked questions
Is Ministral 8B better than Muse Spark 1.2?
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 28.2 on the Noometry Index. Ministral 8B costs 13× 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, Ministral 8B or Muse Spark 1.2?
Ministral 8B is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; Muse Spark 1.2 lists at $1.25 and $4.25.
Is Ministral 8B or Muse Spark 1.2 better for coding?
Muse Spark 1.2 scores higher on coding benchmarks: 49.2 versus 35.0 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 Ministral 8B and Muse Spark 1.2 share?
13 benchmarks have published results for both models. Ministral 8B has 17 scored results on Noometry and Muse Spark 1.2 has 31.