# Mistral Medium 3.5 128B vs Muse Spark 1.1

> Side-by-side benchmark comparison for Mistral Medium 3.5 128B and Muse Spark 1.1 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/mistral-medium-3-5-128b-vs-muse-spark-1-1
- Last updated: October 7, 2026

- Shared sourced benchmarks: 4
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Muse Spark 1.1 leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- Muse Spark 1.1 has the higher overall point estimate 65.95 to 35.36. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in agentic, where the averages are 19.3 for Mistral Medium 3.5 128B and 56.9 for Muse Spark 1.1.
- The biggest single benchmark swing is GPQA Diamond (Vals) in Knowledge, with scores of 34.8% and 91.2%.
- Muse Spark 1.1 also has the larger context window at 1M.

## Model Snapshot

| Property | Mistral Medium 3.5 128B | Muse Spark 1.1 |
|----------|----------|----------|
| Creator | Mistral | Meta |
| Type | Open Weight | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 256K | 1M |
| Overall Score | 35.36 | 65.95 |
| Benchmarks Covered | 7 | 26 |
| Pricing (input/output) | $1.50 / $7.50 | N/A |

## Category Breakdown

### Agentic

- Winner: Muse Spark 1.1
- Mistral Medium 3.5 128B public-lane score: 19.3 (Supported · #102/122)
- Muse Spark 1.1 public-lane score: 56.9 (Supported · #32/122)

| Benchmark | Mistral Medium 3.5 128B | Muse Spark 1.1 | Winner |
|-----------|-----------|-----------|--------|
| τ³-bench results | 91.4% | Coming soon | Coming soon |
| Gert Labs | 39.10% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 39.0% | 69.3% | Muse Spark 1.1 |
| Terminal-Bench 2.1 | Coming soon | 80.0% | Coming soon |
| MCP Atlas | Coming soon | 88.1% | Coming soon |
| Toolathlon | Coming soon | 75.6% | Coming soon |
| OSWorld-Verified | Coming soon | 80.8% | Coming soon |
| WebArena-Verified | Coming soon | 69% | Coming soon |
| DeepSearchQA | Coming soon | 84.9% | Coming soon |
| CyberGym | Coming soon | 59.0% | Coming soon |
| Finance Agent v2 | Coming soon | 57.2% | Coming soon |
| deepSwe | Coming soon | 53.3% | Coming soon |
| OSWorld 2.0 | Coming soon | 14.2% | Coming soon |
| JobBench | Coming soon | 54.7% | Coming soon |
| Cybench | Coming soon | 92.9% | Coming soon |
| ExploitGym | Coming soon | 0.8% | Coming soon |

### Coding

- Winner: Directional only
- Mistral Medium 3.5 128B public-lane score: 24.6 (Estimated · #108/146)
- Muse Spark 1.1 public-lane score: 54.2 (Supported · #35/146)

| Benchmark | Mistral Medium 3.5 128B | Muse Spark 1.1 | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 77.6% | Coming soon | Coming soon |
| SWE-bench (Vals) | 66.4% | 82.0% | Muse Spark 1.1 |
| Terminal-Bench 2.1 | Coming soon | 80.0% | Coming soon |
| SWE-bench Pro | Coming soon | 61.5% | Coming soon |
| LiveCodeBench (Vals) | Coming soon | 85.9% | Coming soon |

### Reasoning

- Winner: Not comparable
- Mistral Medium 3.5 128B public-lane score: 69.9 (Unranked · 2 rankable rows)
- Muse Spark 1.1 public-lane score: 75.7 (Unranked · 3 rankable rows)

| Benchmark | Mistral Medium 3.5 128B | Muse Spark 1.1 | Winner |
|-----------|-----------|-----------|--------|
| MRCR 1M | Coming soon | 54.1% | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- Mistral Medium 3.5 128B public-lane score: 56.7 (Unranked · 1 rankable row)
- Muse Spark 1.1 public-lane score: 78.3 (Unranked · 2 rankable rows)

| Benchmark | Mistral Medium 3.5 128B | Muse Spark 1.1 | Winner |
|-----------|-----------|-----------|--------|
| CharXiv | Coming soon | 88.4% | Coming soon |
| BabyVision | Coming soon | 76.3% | Coming soon |

### Knowledge

- Winner: Muse Spark 1.1
- Mistral Medium 3.5 128B public-lane score: 30.8 (Supported · #137/174)
- Muse Spark 1.1 public-lane score: 66.7 (Supported · #21/174)

| Benchmark | Mistral Medium 3.5 128B | Muse Spark 1.1 | Winner |
|-----------|-----------|-----------|--------|
| GPQA Diamond (Vals) | 34.8% | 91.2% | Muse Spark 1.1 |
| MMLU-Pro (Vals) | 75.3% | 88.7% | Muse Spark 1.1 |
| HLE | Coming soon | 62.1% | Coming soon |
| HLE w/o tools | Coming soon | 52.2% | Coming soon |
| HealthBench Professional | Coming soon | 59.3% | Coming soon |

### Instruction Following

- Winner: Not comparable
- Mistral Medium 3.5 128B public-lane score: 82.6 (#47/125)
- Muse Spark 1.1 public-lane score: Coming soon

## FAQ

### Which is better overall, Mistral Medium 3.5 128B or Muse Spark 1.1?

Muse Spark 1.1 has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between Mistral Medium 3.5 128B and Muse Spark 1.1?

The widest category gap is in agentic, where the averages are 19.3 for Mistral Medium 3.5 128B and 56.9 for Muse Spark 1.1.

### How many benchmarks does Mistral Medium 3.5 128B cover on BenchLM?

Mistral Medium 3.5 128B currently has 7 sourced benchmark scores on BenchLM.

### How many benchmarks does Muse Spark 1.1 cover on BenchLM?

Muse Spark 1.1 currently has 26 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Mistral Medium 3.5 128B vs Muse Spark 1.2](/compare/mistral-medium-3-5-128b-vs-muse-spark-1-2)
- [Muse Spark 1.1 vs Muse Spark 1.2](/compare/muse-spark-1-1-vs-muse-spark-1-2)
- [Mistral Medium 3.5 128B vs Muse Spark](/compare/mistral-medium-3-5-128b-vs-muse-spark)
- [Muse Spark 1.1 vs Muse Spark](/compare/muse-spark-vs-muse-spark-1-1)

## Explore More

- [Mistral Medium 3.5 128B profile](/models/mistral-medium-3-5-128b)
- [Muse Spark 1.1 profile](/models/muse-spark-1-1)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)