# Mistral Small 3.1 vs Qwen3-Coder 480B-A35B Instruct

> Qwen3-Coder 480B-A35B Instruct is the stronger model overall, scoring 37.7 to 31.4 on the Noometry Index. Mistral Small 3.1 costs 7.5× less per token, which makes it the better buy when Qwen3-Coder 480B-A35B Instruct's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/mistral-small-3-1-vs-qwen3-coder-480b-a35b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Mistral Small 3.1 scores higher in 1 category and Qwen3-Coder 480B-A35B Instruct in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3-Coder 480B-A35B Instruct leads 34.9 to 13.7.
- Mistral Small 3.1 is cheaper at $0.35 / $0.56 per million input/output tokens, against $1.50 / $7.50 for Qwen3-Coder 480B-A35B Instruct.
- Qwen3-Coder 480B-A35B Instruct accepts more context: 262K tokens versus 128K.

## Snapshot

| | Mistral Small 3.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.4 | 37.7 |
| Rank | 263 | 186 |
| Context | 128K | 262K |
| Input $/M | $0.35 | $1.50 |
| Output $/M | $0.56 | $7.50 |
| Weights | Open | Open |

## Coding

- Mistral Small 3.1: 37.7 (#175)
- Qwen3-Coder 480B-A35B Instruct: 36.2 (#199)

| Benchmark | Mistral Small 3.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Coding | 1309 | 1413 |
| SWE-bench Verified (bash only) | — | 55.4% |
| LMArena WebDev | — | 1275 |
| GSO | — | 4.9% |
| WeirdML | — | 41.2% |
| ALE-Bench | — | 461.45 |
| AlgoTune | — | 1.44 |

## Agentic & Tool Use

- Mistral Small 3.1: —
- Qwen3-Coder 480B-A35B Instruct: 23.7 (#116)

| Benchmark | Mistral Small 3.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | — | 27.2% |

## Reasoning

- Mistral Small 3.1: 18.9 (#249)
- Qwen3-Coder 480B-A35B Instruct: 24.7 (#141)

| Benchmark | Mistral Small 3.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1278 | 1372 |
| Kagi LLM Benchmark | — | 49.5% |
| Chess Puzzles | 1% | — |
| Epoch Capabilities Index | 127.48 | — |

## Math

- Mistral Small 3.1: 13.7 (#295)
- Qwen3-Coder 480B-A35B Instruct: 34.9 (#151)

| Benchmark | Mistral Small 3.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | 1261 | 1364 |
| OTIS Mock AIME 2024-2025 | 3.9% | — |
| Omni-MATH | 24.8% | — |

## Knowledge

- Mistral Small 3.1: 22.6 (#266)
- Qwen3-Coder 480B-A35B Instruct: 36.4 (#159)

| Benchmark | Mistral Small 3.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Expert | 1258 | 1337 |
| GPQA Diamond | 41.9% | — |
| MMLU-Pro | 61% | — |
| GPQA (HELM) | 39.2% | — |

## Multimodal

- Mistral Small 3.1: 32.6 (#93)
- Qwen3-Coder 480B-A35B Instruct: —

| Benchmark | Mistral Small 3.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Vision | 1136 | — |

## Multilingual

- Mistral Small 3.1: 41.4 (#204)
- Qwen3-Coder 480B-A35B Instruct: 47.8 (#143)

| Benchmark | Mistral Small 3.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | 1255 | 1345 |
| LMArena Chinese | 1254 | 1356 |
| LMArena French | 1270 | 1394 |
| LMArena German | 1266 | 1324 |
| LMArena Japanese | 1210 | 1309 |
| LMArena Korean | 1206 | 1307 |
| LMArena Russian | 1263 | 1367 |
| LMArena Spanish | 1283 | 1360 |

## Instruction Following

- Mistral Small 3.1: 63.8 (#225)
- Qwen3-Coder 480B-A35B Instruct: 71.8 (#142)

| Benchmark | Mistral Small 3.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | 1264 | 1356 |
| IFEval | 75% | — |

## Long Context

- Mistral Small 3.1: 39.5 (#172)
- Qwen3-Coder 480B-A35B Instruct: 42.0 (#126)

| Benchmark | Mistral Small 3.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | 1300 | 1379 |

## Writing & Preference

- Mistral Small 3.1: 37.2 (#254)
- Qwen3-Coder 480B-A35B Instruct: 55.5 (#142)

| Benchmark | Mistral Small 3.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | 1278 | 1356 |
| LMArena Creative Writing | 1253 | 1333 |
| LMArena Multi-Turn | 1270 | 1365 |
| EQ-Bench Creative Writing | 761 | — |
| WildBench | 78.8% | — |

## FAQ

### Is Mistral Small 3.1 better than Qwen3-Coder 480B-A35B Instruct?

Qwen3-Coder 480B-A35B Instruct is the stronger model overall, scoring 37.7 to 31.4 on the Noometry Index. Mistral Small 3.1 costs 7.5× less per token, which makes it the better buy when Qwen3-Coder 480B-A35B Instruct's lead doesn't matter for your workload.

### Which is cheaper, Mistral Small 3.1 or Qwen3-Coder 480B-A35B Instruct?

Mistral Small 3.1 is cheaper. It lists at $0.35 per million input tokens and $0.56 per million output tokens; Qwen3-Coder 480B-A35B Instruct lists at $1.50 and $7.50.

### Is Mistral Small 3.1 or Qwen3-Coder 480B-A35B Instruct better for coding?

Mistral Small 3.1 scores higher on coding benchmarks: 37.7 versus 36.2 in the Noometry coding category.

### Which has the bigger context window?

Qwen3-Coder 480B-A35B Instruct does, with 262K tokens against 128K.

### How many benchmarks do Mistral Small 3.1 and Qwen3-Coder 480B-A35B Instruct share?

17 benchmarks have published results for both models. Mistral Small 3.1 has 28 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.