# Devstral Small vs K-Exaone

> Side-by-side benchmark comparison for Devstral Small and K-Exaone across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/devstral-small-vs-k-exaone
- Last updated: October 14, 2026

- Shared sourced benchmarks: 1
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Evidence is too thin for a benchmark verdict: Devstral Small and K-Exaone share only 1 sourced benchmark row.

## Summary

- Only 1 shared sourced benchmark row is available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- K-Exaone has the larger published context window at 256K.

## Model Snapshot

| Property | Devstral Small | K-Exaone |
|----------|----------|----------|
| Creator | Mistral | LG AI Research |
| Type | Open Weight | Proprietary |
| Reasoning | Non-Reasoning | Reasoning |
| Context | 128K | 256K |
| Independent public score (not head-to-head) | null | 37.38 |
| Benchmarks Covered | 1 | 1 |
| Pricing (input/output) | N/A | N/A |

## Category Breakdown

### Coding

- Winner: Insufficient shared evidence
- Devstral Small public-lane score: Coming soon
- K-Exaone public-lane score: 23.2 (Estimated · #112/149)

| Benchmark | Devstral Small | K-Exaone | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 46.8% | 49.4% | K-Exaone |

### Reasoning

- Winner: Insufficient shared evidence
- Devstral Small public-lane score: Coming soon
- K-Exaone public-lane score: 68 (Unranked · 2 rankable rows)

### Knowledge

- Winner: Insufficient shared evidence
- Devstral Small public-lane score: Coming soon
- K-Exaone public-lane score: 36.1 (Estimated · #128/181)

### Instruction Following

- Winner: Insufficient shared evidence
- Devstral Small public-lane score: Coming soon
- K-Exaone public-lane score: 78.7 (Unranked · 1 rankable row)

## FAQ

### Is there enough evidence to pick between Devstral Small and K-Exaone?

Not yet. The models share only 1 sourced benchmark row, 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

- [Devstral Small vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-devstral-small)
- [K-Exaone vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-k-exaone)
- [Devstral Small vs GPT-6.1 Sol](/compare/devstral-small-vs-gpt-6-1-sol)
- [K-Exaone vs GPT-6.1 Sol](/compare/gpt-6-1-sol-vs-k-exaone)

## Explore More

- [Devstral Small profile](/models/devstral-small)
- [K-Exaone profile](/models/k-exaone)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)