# Claude Opus 5.5 vs Devstral Medium

> Claude Opus 5.5 has enough public results to be ranked (#3); Devstral Medium does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/claude-opus-5-5-vs-devstral-medium
- Last updated: 2026-10-11
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. Claude Opus 5.5 scores higher in 2 categories and Devstral Medium in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Opus 5.5 leads 80.2 to 21.1.
- Devstral Medium is cheaper at $0.40 / $2 per million input/output tokens, against $4 / $20 for Claude Opus 5.5.
- Claude Opus 5.5 accepts more context: 1M tokens versus 262K.
- Devstral Medium has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Opus 5.5 | Devstral Medium |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 68.6 | 30.1 |
| Rank | 3 | — |
| Context | 1M | 262K |
| Input $/M | $4 | $0.40 |
| Output $/M | $20 | $2 |
| Weights | Proprietary | Open |

## Coding

- Claude Opus 5.5: 71.9 (#3)
- Devstral Medium: 24.3

| Benchmark | Claude Opus 5.5 | Devstral Medium |
|---|---|---|
| LMArena WebDev | 1813 | 1076 |
| FrontierCode | 54.6% | — |
| CursorBench | 57.8% | — |
| FrontierSWE | 62.3% | — |
| SciCode | 66.9% | — |
| LMArena Coding | 1547 | — |
| MirrorCode | 77.4% | — |
| ALE-Bench | 2,147 | — |

## Agentic & Tool Use

- Claude Opus 5.5: 45.3 (#15)
- Devstral Medium: —

| Benchmark | Claude Opus 5.5 | Devstral Medium |
|---|---|---|
| APEX-Agents | 73.5% | — |
| GDP.pdf | 30.6% | — |
| Vending-Bench 2 | 9,235 | — |

## Reasoning

- Claude Opus 5.5: 80.2 (#3)
- Devstral Medium: 21.1

| Benchmark | Claude Opus 5.5 | Devstral Medium |
|---|---|---|
| ARC-AGI-2 | 93.3% | — |
| Kagi LLM Benchmark | — | 37.7% |
| NYT Connections (extended) | 88.5% | — |
| ARC-AGI-1 | 98.5% | — |
| CritPt | 31.7% | — |
| EBR-Bench | 71.4% | — |
| LMArena Hard Prompts | 1535 | — |
| Mystery Game Puzzles | 71% | — |
| DTBench | 98.9% | — |
| LMCA | 68.2% | — |
| Epoch Capabilities Index | 167.33 | — |

## Math

- Claude Opus 5.5: 91.8 (#3)
- Devstral Medium: —

| Benchmark | Claude Opus 5.5 | Devstral Medium |
|---|---|---|
| FrontierMath (Tiers 1-3) | 91.2% | — |
| FrontierMath Tier 4 | 95% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 100% | — |
| LMArena Math | 1506 | — |
| FrontierMath Erdős | 2.9% | — |

## Knowledge

- Claude Opus 5.5: 66.4 (#10)
- Devstral Medium: —

| Benchmark | Claude Opus 5.5 | Devstral Medium |
|---|---|---|
| GPQA Diamond | 90.6% | — |
| SimpleQA Verified | 72.2% | — |
| LMArena Expert | 1547 | — |

## Multimodal

- Claude Opus 5.5: 57.8 (#1)
- Devstral Medium: —

| Benchmark | Claude Opus 5.5 | Devstral Medium |
|---|---|---|
| LMArena Vision | 1321 | — |
| Blueprint-Bench 2 | 51.2% | — |
| Furniture Assembly | 83.3% | — |

## Multilingual

- Claude Opus 5.5: 59.1 (#2)
- Devstral Medium: —

| Benchmark | Claude Opus 5.5 | Devstral Medium |
|---|---|---|
| LMArena Non-English | 1507 | — |
| LMArena Chinese | 1588 | — |
| LMArena French | 1514 | — |
| LMArena Russian | 1520 | — |
| LMArena Spanish | 1507 | — |

## Instruction Following

- Claude Opus 5.5: 80.0 (#3)
- Devstral Medium: —

| Benchmark | Claude Opus 5.5 | Devstral Medium |
|---|---|---|
| LMArena Instruction Following | 1537 | — |

## Long Context

- Claude Opus 5.5: 47.1 (#19)
- Devstral Medium: —

| Benchmark | Claude Opus 5.5 | Devstral Medium |
|---|---|---|
| LMArena Longer Query | 1532 | — |

## Writing & Preference

- Claude Opus 5.5: 78.2 (#3)
- Devstral Medium: —

| Benchmark | Claude Opus 5.5 | Devstral Medium |
|---|---|---|
| LMArena Text | 1515 | — |
| LMArena Creative Writing | 1533 | — |
| EQ-Bench Creative Writing | 2050 | — |
| LMArena Multi-Turn | 1499 | — |

## FAQ

### Is Claude Opus 5.5 better than Devstral Medium?

Claude Opus 5.5 has enough public results to be ranked (#3); Devstral Medium does not yet, so treat this comparison as directional.

### Which is cheaper, Claude Opus 5.5 or Devstral Medium?

Devstral Medium is cheaper. It lists at $0.40 per million input tokens and $2 per million output tokens; Claude Opus 5.5 lists at $4 and $20.

### Is Claude Opus 5.5 or Devstral Medium better for coding?

Claude Opus 5.5 scores higher on coding benchmarks: 71.9 versus 24.3 in the Noometry coding category.

### Which has the bigger context window?

Claude Opus 5.5 does, with 1M tokens against 262K.

### How many benchmarks do Claude Opus 5.5 and Devstral Medium share?

1 benchmark has published results for both models. Claude Opus 5.5 has 44 scored results on Noometry and Devstral Medium has 2.