# GPT-OSS 20B vs Magistral Medium

> Side-by-side benchmark comparison for GPT-OSS 20B and Magistral Medium across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/gpt-oss-20b-vs-magistral-medium
- Last updated: October 14, 2026

- Shared sourced benchmarks: 3
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Evidence is too thin for a benchmark verdict: GPT-OSS 20B and Magistral Medium share only 3 sourced benchmark rows.

## Summary

- Only 3 shared sourced benchmark rows are available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- GPT-OSS 20B has the larger published context window at 128K.

## Model Snapshot

| Property | GPT-OSS 20B | Magistral Medium |
|----------|----------|----------|
| Creator | OpenAI | Mistral |
| Type | Open Weight | Proprietary |
| Reasoning | Non-Reasoning | Reasoning |
| Context | 128K | 40K |
| Independent public score (not head-to-head) | 33.13 | null |
| Benchmarks Covered | 7 | 6 |
| Pricing (input/output) | $0.00 / $0.00 | N/A |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- GPT-OSS 20B public-lane score: 14.6 (Estimated · #112/124)
- Magistral Medium public-lane score: Coming soon

### Coding

- Winner: Insufficient shared evidence
- GPT-OSS 20B public-lane score: 18.6 (Estimated · #122/149)
- Magistral Medium public-lane score: Coming soon

| Benchmark | GPT-OSS 20B | Magistral Medium | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 60.7% | Coming soon | Coming soon |
| React Native Evals | 71% | Coming soon | Coming soon |
| LiveCodeBench v5 | Coming soon | 59.4% | Coming soon |
| LiveCodeBench v6 | Coming soon | 50.3% | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- GPT-OSS 20B public-lane score: 49.7 (Unranked · 2 rankable rows)
- Magistral Medium public-lane score: Coming soon

### Knowledge

- Winner: Insufficient shared evidence
- GPT-OSS 20B public-lane score: 34.1 (Supported · #137/181)
- Magistral Medium public-lane score: Coming soon

| Benchmark | GPT-OSS 20B | Magistral Medium | Winner |
|-----------|-----------|-----------|--------|
| MMLU | 85.3% | Coming soon | Coming soon |
| GPQA | 71.5% | 70.8% | GPT-OSS 20B |
| HLE | 10.9% | Coming soon | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- GPT-OSS 20B public-lane score: 79.2 (#57/128)
- Magistral Medium public-lane score: Coming soon

### Mathematics

- Winner: Insufficient shared evidence
- GPT-OSS 20B public-lane score: Coming soon
- Magistral Medium public-lane score: Coming soon

| Benchmark | GPT-OSS 20B | Magistral Medium | Winner |
|-----------|-----------|-----------|--------|
| AIME 2024 | 92.1% | 73.6% | GPT-OSS 20B |
| AIME 2025 | 91.7% | 64.9% | GPT-OSS 20B |
| MATH-500 | Coming soon | 94.3% | Coming soon |

## FAQ

### Is there enough evidence to pick between GPT-OSS 20B and Magistral Medium?

Not yet. The models share only 3 sourced benchmark rows, so this mirror reports the available measurements and metadata without naming a broad winner.

### What can I compare safely on this page?

Published pricing, context windows, model type, and individual shared benchmark rows are directly comparable. Independent overall scores and non-overlapping benchmark coverage are labeled separately and should not be read as a controlled head-to-head result.

## Related Comparisons

- [GPT-OSS 20B vs GPT-OSS 120B](/compare/gpt-oss-120b-vs-gpt-oss-20b)
- [Magistral Medium vs GPT-OSS 120B](/compare/gpt-oss-120b-vs-magistral-medium)
- [GPT-OSS 20B vs Magistral Small](/compare/gpt-oss-20b-vs-magistral-small)
- [Magistral Medium vs Magistral Small](/compare/magistral-medium-vs-magistral-small)

## Explore More

- [GPT-OSS 20B profile](/models/gpt-oss-20b)
- [Magistral Medium profile](/models/magistral-medium)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)