# Mistral Medium 3.5 128B vs Qwen3.8-27B

> Side-by-side benchmark comparison for Mistral Medium 3.5 128B and Qwen3.8-27B across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/mistral-medium-3-5-128b-vs-qwen3-8-27b
- Last updated: September 28, 2026

- Shared sourced benchmarks: 4
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.7

## Quick Verdict

Pick Qwen3.8-27B if you want the stronger benchmark profile. Mistral Medium 3.5 128B only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Qwen3.8-27B leads overall 55.26 to 36.23.
- The clearest category separation is in agentic, where the averages are 19.7 for Mistral Medium 3.5 128B and 61.2 for Qwen3.8-27B.
- The biggest single benchmark swing is GPQA Diamond (Vals) in Knowledge, with scores of 34.8% and 88.9%.
- Qwen3.8-27B is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Qwen3.8-27B also has the larger context window at 262K.

## Model Snapshot

| Property | Mistral Medium 3.5 128B | Qwen3.8-27B |
|----------|----------|----------|
| Creator | Mistral | Alibaba |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 256K | 262K |
| Overall Score | 36.23 | 55.26 |
| Benchmarks Covered | 7 | 33 |
| Pricing (input/output) | $1.50 / $7.50 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Qwen3.8-27B
- Mistral Medium 3.5 128B public-lane score: 19.7 (Supported · #99/117)
- Qwen3.8-27B public-lane score: 61.2 (Supported · #18/117)

| Benchmark | Mistral Medium 3.5 128B | Qwen3.8-27B | 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% | 58.4% | Qwen3.8-27B |
| Terminal-Bench 2.1 | Coming soon | 73.0% | Coming soon |
| CoWorkBench | Coming soon | 70.7% | Coming soon |
| JobBench | Coming soon | 33.4% | Coming soon |
| Agents' Last Exam | Coming soon | 42.9% | Coming soon |
| OSWorld-Verified | Coming soon | 84.3% | Coming soon |
| WebArena-Verified | Coming soon | 64.8% | Coming soon |
| AndroidWorld | Coming soon | 81.9% | Coming soon |

### Coding

- Winner: Directional only
- Mistral Medium 3.5 128B public-lane score: 26.7 (Estimated · #101/142)
- Qwen3.8-27B public-lane score: 48.7 (Supported · #45/142)

| Benchmark | Mistral Medium 3.5 128B | Qwen3.8-27B | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 77.6% | Coming soon | Coming soon |
| SWE-bench (Vals) | 66.4% | 86.0% | Qwen3.8-27B |
| Terminal-Bench 2.1 | Coming soon | 73.0% | Coming soon |
| SWE-bench Pro | Coming soon | 61.7% | Coming soon |
| NL2Repo | Coming soon | 42.3% | Coming soon |
| DeepSWE | Coming soon | 42.2% | Coming soon |
| LiveCodeBench v6 | Coming soon | 90.3% | Coming soon |
| VulcanBench v3 | Coming soon | 82.6% | Coming soon |
| LiveCodeBench (Vals) | Coming soon | 84.0% | Coming soon |

### Reasoning

- Winner: Not comparable
- Mistral Medium 3.5 128B public-lane score: 69.9 (Unranked · 2 rankable rows)
- Qwen3.8-27B public-lane score: 78.7 (#8/27)

### Multimodal & Grounded

- Winner: Not comparable
- Mistral Medium 3.5 128B public-lane score: 56.7 (Unranked · 1 rankable row)
- Qwen3.8-27B public-lane score: 80.9 (#11/50)

| Benchmark | Mistral Medium 3.5 128B | Qwen3.8-27B | Winner |
|-----------|-----------|-----------|--------|
| MathVision | Coming soon | 90.0% | Coming soon |
| MathVision w/ Python | Coming soon | 94.6% | Coming soon |
| BabyVision | Coming soon | 65.7% | Coming soon |
| BabyVision w/ Python | Coming soon | 85.6% | Coming soon |
| Vision2Web | Coming soon | 62.9% | Coming soon |
| CharXiv w/o tools | Coming soon | 83.7% | Coming soon |
| CharXiv | Coming soon | 90.2% | Coming soon |
| OmniDocBench 1.5 | Coming soon | 91.1% | Coming soon |
| RealWorldQA | Coming soon | 85.9% | Coming soon |
| ERQA | Coming soon | 65.5% | Coming soon |

### Knowledge

- Winner: Qwen3.8-27B
- Mistral Medium 3.5 128B public-lane score: 33.8 (Supported · #119/168)
- Qwen3.8-27B public-lane score: 49.2 (Supported · #63/168)

| Benchmark | Mistral Medium 3.5 128B | Qwen3.8-27B | Winner |
|-----------|-----------|-----------|--------|
| GPQA Diamond (Vals) | 34.8% | 88.9% | Qwen3.8-27B |
| MMLU-Pro (Vals) | 75.3% | 84.3% | Qwen3.8-27B |
| GPQA | Coming soon | 89.2% | Coming soon |
| GPQA-D | Coming soon | 89.2% | Coming soon |
| HLE | Coming soon | 30.8% | Coming soon |
| HLE w/o tools | Coming soon | 30.8% | Coming soon |

### Instruction Following

- Winner: Directional only
- Mistral Medium 3.5 128B public-lane score: 82.6 (#48/124)
- Qwen3.8-27B public-lane score: 83.2 (#45/124)

| Benchmark | Mistral Medium 3.5 128B | Qwen3.8-27B | Winner |
|-----------|-----------|-----------|--------|
| IFBench | Coming soon | 79.5% | Coming soon |

## FAQ

### Which is better overall, Mistral Medium 3.5 128B or Qwen3.8-27B?

Qwen3.8-27B is ahead overall on BenchLM right now.

### Where is the biggest gap between Mistral Medium 3.5 128B and Qwen3.8-27B?

The widest category gap is in agentic, where the averages are 19.7 for Mistral Medium 3.5 128B and 61.2 for Qwen3.8-27B.

### 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 Qwen3.8-27B cover on BenchLM?

Qwen3.8-27B currently has 33 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Mistral Medium 3.5 128B vs GPT-6 Astra](/compare/gpt-6-astra-vs-mistral-medium-3-5-128b)
- [Qwen3.8-27B vs GPT-6 Astra](/compare/gpt-6-astra-vs-qwen3-8-27b)
- [Mistral Medium 3.5 128B vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-mistral-medium-3-5-128b)
- [Qwen3.8-27B vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-qwen3-8-27b)

## Explore More

- [Mistral Medium 3.5 128B profile](/models/mistral-medium-3-5-128b)
- [Qwen3.8-27B profile](/models/qwen3-8-27b)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)