Model comparison
Mistral Medium 3.5 128B vs Muse Spark
Head-to-head evidence from 17 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Mistral Medium 3.5 128B unranked (Not scored); Muse Spark #16 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Mistral Medium 3.5 128B and Muse Spark share 17 comparable benchmark results. 1 of 8 categories are comparable. 8 results are unique to Mistral Medium 3.5 128B; 22 to Muse Spark.
Updated July 27, 2026- Shared results
- 17
- Mistral Medium 3.5 128B only
- 8
- Muse Spark only
- 22
- Comparable categories
- 1 / 8
Treat this as a split decision. Mistral Medium 3.5 128B makes more sense if coding is the priority; Muse Spark is the better fit if you need the larger 262K context window.
Confidence note. This is a partial-evidence comparison with 17 shared benchmark results across 6 evidence categories; 1 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
Mistral Medium 3.5 128B and Muse Spark finish on the same BenchAlign overall score, so this is less about a single winner and more about where the edge shows up. The BenchAlign headline says tie; the benchmark table is where the real choice happens.
Muse Spark gives you the larger context window at 262K, compared with 256K for Mistral Medium 3.5 128B.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | Mistral Medium 3.5 128B | Δ | Muse Spark |
|---|---|---|---|
| Coding | Mistral Medium 3.5 128B77.6 | Margin← 9.8 | Muse Spark67.8 |
| Agentic | Mistral Medium 3.5 128BNot measured | MarginNo overlap | Muse Spark59.0 |
| Reasoning | Mistral Medium 3.5 128BNot measured | MarginNo overlap | Muse Spark42.5 |
| Knowledge | Mistral Medium 3.5 128BNot measured | MarginNo overlap | Muse Spark50.4 |
| Math | Mistral Medium 3.5 128BNot measured | MarginNo overlap | Muse Spark32.9 |
| Multimodal | Mistral Medium 3.5 128BNot measured | MarginNo overlap | Muse Spark82.5 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
SWE-bench Verified
CodingA 77.6%B 77.4%Winner: Mistral Medium 3.5 128BΔ 0.2SWE-bench Verified: Mistral Medium 3.5 128B scored 77.6%; Muse Spark scored 77.4%. Mistral Medium 3.5 128B wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Mistral Medium 3.5 128B | Muse Spark | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Mistral Medium 3.5 128B$1.5 input / $7.5 output | Muse SparkNot available | A complete price comparison is not available. |
| Generation speedtokens per second | Mistral Medium 3.5 128BNot available | Muse SparkNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Mistral Medium 3.5 128BNot available | Muse SparkNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Mistral Medium 3.5 128B256K | Muse Spark262K | Muse Spark lists the larger context window. |
Benchmark Deep Dive
Agentic15 benchmarks
| Benchmark | Mistral Medium 3.5 128B | Muse Spark | Result |
|---|---|---|---|
| τ³-bench resultsSource | 91.4% | — | Not comparable |
| AA Agentic IndexSource | 19.0% | 28.7% | Muse Spark leads |
| τ²-bench resultsSource | 94.2% | 91.5% | Mistral Medium 3.5 128B leads |
| GDPval-AASource | 21.6% | 32.2% | Muse Spark leads |
| GDPval-AASource | 933 | 1143 | Muse Spark leads |
| Gert LabsSource | 39.10% | — | Not comparable |
| AA EnterpriseOps-GymSource | 33.7% | — | Not comparable |
| AA Harvey LABSource | 69.1% | — | Not comparable |
| terminalBenchHardSource | 33.3% | — | Not comparable |
| AA BriefcaseSource | 516 | — | Not comparable |
| AA Tau3 BankingSource | 14.4% | — | Not comparable |
| Terminal-Bench 2.0Source | — | 59% | Not comparable |
| DeepSearchQASource | — | 74.8% | Not comparable |
| CyberGymSource | — | 43.5% | Not comparable |
| Claw-EvalSource | — | 63.8% | Not comparable |
CodingMistral Medium 3.5 128B wins6 benchmarks
| Benchmark | Mistral Medium 3.5 128B | Muse Spark | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 77.6% | 77.4% | Mistral Medium 3.5 128B leads |
| AA Coding IndexSource | 46.9% | 58.6% | Muse Spark leads |
| AA-SciCodeSource | 39.6% | 51.5% | Muse Spark leads |
| SWE-bench ProSource | — | 52.4% | Not comparable |
| LiveCodeBench ProSource | — | 80.0% | Not comparable |
| Vibe Code BenchSource | — | 19.67% | Not comparable |
Reasoning3 benchmarks
Knowledge12 benchmarks
| Benchmark | Mistral Medium 3.5 128B | Muse Spark | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | 29.9% | 43.1% | Muse Spark leads |
| AA-GPQA DiamondSource | 74.8% | 88.4% | Muse Spark leads |
| AA-HLESource | 12.8% | 39.9% | Muse Spark leads |
| AA-Omniscience IndexSource | -36.3% | 4.1% | Muse Spark leads |
| AA-Omniscience AccuracySource | 25.1% | 44.6% | Muse Spark leads |
| AA-Omniscience Hallucination RateSource | 82.0% | 73.2% | Muse Spark leads |
| AA Openness IndexSource | 33.3% | — | Not comparable |
| GPQA-DSource | — | 89.5% | Not comparable |
| HLESource | — | 50.4% | Not comparable |
| HLE w/o toolsSource | — | 42.8% | Not comparable |
| HealthBench HardSource | — | 42.8% | Not comparable |
| MedXpertQA (Text)Source | — | 52.6% | Not comparable |
Math2 benchmarks
Multimodal8 benchmarks
| Benchmark | Mistral Medium 3.5 128B | Muse Spark | Result |
|---|---|---|---|
| AA-MMMU-ProSource | 64.9% | 80.5% | Muse Spark leads |
| CharXivSource | — | 86.4% | Not comparable |
| MMMU-ProSource | — | 80.4% | Not comparable |
| ERQASource | — | 64.7% | Not comparable |
| SimpleVQASource | — | 71.3% | Not comparable |
| ScreenSpot ProSource | — | 84.1% | Not comparable |
| ZeroBenchSource | — | 33.0% | Not comparable |
| MedXpertQA (MM)Source | — | 78.4% | Not comparable |
Inst. Following1 benchmarks
| Benchmark | Mistral Medium 3.5 128B | Muse Spark | Result |
|---|---|---|---|
| AA-IFBenchSource | 68.8% | 75.9% | Muse Spark leads |
Frequently Asked Questions (2)
Which is better, Mistral Medium 3.5 128B or Muse Spark?
Mistral Medium 3.5 128B and Muse Spark are tied on the BenchAlign overall score, so the right pick depends on which category matters most for your use case.
Which is better for coding, Mistral Medium 3.5 128B or Muse Spark?
Mistral Medium 3.5 128B has the edge for coding in this comparison, averaging 77.6 versus 67.8. Inside this category, AA-SciCode is the benchmark that creates the most daylight between them.
Related Comparisons
Explore More
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
One email each week. Unsubscribe anytime.