# Olmo 3.1 32b Instruct vs Qwen Max

> Olmo 3.1 32b Instruct is the stronger model overall, scoring 38.8 to 34.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/olmo-3-1-32b-instruct-vs-qwen-max
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. Olmo 3.1 32b Instruct scores higher in 8 categories and Qwen Max in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Olmo 3.1 32b Instruct leads 33.6 to 21.0.
- Olmo 3.1 32b Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Olmo 3.1 32b Instruct | Qwen Max |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | Alibaba (Qwen) |
| Noometry Index | 38.8 | 34.4 |
| Rank | 168 | 226 |
| Context | — | 33K |
| Input $/M | — | $1.60 |
| Output $/M | — | $6.40 |
| Weights | Open | Proprietary |

## Coding

- Olmo 3.1 32b Instruct: 38.9 (#154)
- Qwen Max: 30.3 (#288)

| Benchmark | Olmo 3.1 32b Instruct | Qwen Max |
|---|---|---|
| LMArena Coding | 1346 | 1288 |
| Aider Polyglot | — | 21.8% |

## Reasoning

- Olmo 3.1 32b Instruct: 25.4 (#131)
- Qwen Max: 24.1 (#154)

| Benchmark | Olmo 3.1 32b Instruct | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1322 | 1270 |

## Math

- Olmo 3.1 32b Instruct: 33.6 (#169)
- Qwen Max: 21.0 (#272)

| Benchmark | Olmo 3.1 32b Instruct | Qwen Max |
|---|---|---|
| LMArena Math | 1305 | 1275 |
| OTIS Mock AIME 2024-2025 | — | 16.1% |
| MATH Level 5 | — | 67.2% |
| FrontierMath (Feb 2025 set) | — | 1% |

## Knowledge

- Olmo 3.1 32b Instruct: 35.4 (#175)
- Qwen Max: 30.3 (#222)

| Benchmark | Olmo 3.1 32b Instruct | Qwen Max |
|---|---|---|
| LMArena Expert | 1307 | 1248 |
| GPQA Diamond | — | 56.1% |

## Multilingual

- Olmo 3.1 32b Instruct: 42.8 (#185)
- Qwen Max: 42.0 (#197)

| Benchmark | Olmo 3.1 32b Instruct | Qwen Max |
|---|---|---|
| LMArena Non-English | 1275 | 1263 |
| LMArena Chinese | 1304 | 1254 |
| LMArena French | 1328 | 1329 |
| LMArena German | 1283 | 1254 |
| LMArena Korean | 1206 | 1141 |
| LMArena Russian | 1268 | 1274 |
| LMArena Spanish | 1337 | 1290 |
| LMArena Japanese | — | 1205 |

## Instruction Following

- Olmo 3.1 32b Instruct: 68.8 (#182)
- Qwen Max: 66.7 (#203)

| Benchmark | Olmo 3.1 32b Instruct | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1298 | 1262 |

## Long Context

- Olmo 3.1 32b Instruct: 39.9 (#161)
- Qwen Max: 39.4 (#175)

| Benchmark | Olmo 3.1 32b Instruct | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1312 | 1289 |
| Fiction.LiveBench | — | 66.7% |

## Writing & Preference

- Olmo 3.1 32b Instruct: 50.4 (#179)
- Qwen Max: 48.0 (#200)

| Benchmark | Olmo 3.1 32b Instruct | Qwen Max |
|---|---|---|
| LMArena Text | 1311 | 1282 |
| LMArena Creative Writing | 1264 | 1248 |
| LMArena Multi-Turn | 1309 | 1277 |

## FAQ

### Is Olmo 3.1 32b Instruct better than Qwen Max?

Olmo 3.1 32b Instruct is the stronger model overall, scoring 38.8 to 34.4 on the Noometry Index.

### Is Olmo 3.1 32b Instruct or Qwen Max better for coding?

Olmo 3.1 32b Instruct scores higher on coding benchmarks: 38.9 versus 30.3 in the Noometry coding category.

### How many benchmarks do Olmo 3.1 32b Instruct and Qwen Max share?

16 benchmarks have published results for both models. Olmo 3.1 32b Instruct has 16 scored results on Noometry and Qwen Max has 23.