# Olmo 3.1 32b Instruct vs Qwen2.5 72B Instruct

> Olmo 3.1 32b Instruct is the stronger model overall, scoring 39.4 to 31.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/olmo-3-1-32b-instruct-vs-qwen2-5-72b-instruct
- Last updated: 2026-10-12
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. Olmo 3.1 32b Instruct scores higher in 8 categories and Qwen2.5 72B Instruct in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Olmo 3.1 32b Instruct leads 36.3 to 19.3.

## Snapshot

| | Olmo 3.1 32b Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | Alibaba (Qwen) |
| Noometry Index | 39.4 | 31.9 |
| Rank | 168 | 267 |
| Context | — | 131K |
| Input $/M | — | $1.40 |
| Output $/M | — | $5.60 |
| Weights | Open | Open |

## Coding

- Olmo 3.1 32b Instruct: 39.5 (#157)
- Qwen2.5 72B Instruct: 33.2 (#260)

| Benchmark | Olmo 3.1 32b Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 1347 | 1292 |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |

## Agentic & Tool Use

- Olmo 3.1 32b Instruct: —
- Qwen2.5 72B Instruct: 22.1 (#133)

| Benchmark | Olmo 3.1 32b Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |

## Reasoning

- Olmo 3.1 32b Instruct: 26.4 (#132)
- Qwen2.5 72B Instruct: 22.3 (#199)

| Benchmark | Olmo 3.1 32b Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1322 | 1271 |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| Epoch Capabilities Index | — | 129 |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |

## Math

- Olmo 3.1 32b Instruct: 36.3 (#167)
- Qwen2.5 72B Instruct: 19.3 (#287)

| Benchmark | Olmo 3.1 32b Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Math | 1305 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |

## Knowledge

- Olmo 3.1 32b Instruct: 36.1 (#175)
- Qwen2.5 72B Instruct: 27.0 (#253)

| Benchmark | Olmo 3.1 32b Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Expert | 1308 | 1245 |
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |

## Multilingual

- Olmo 3.1 32b Instruct: 42.6 (#191)
- Qwen2.5 72B Instruct: 41.0 (#213)

| Benchmark | Olmo 3.1 32b Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1275 | 1252 |
| LMArena Chinese | 1304 | 1272 |
| LMArena French | 1328 | 1280 |
| LMArena German | 1282 | 1234 |
| LMArena Korean | 1206 | 1188 |
| LMArena Russian | 1268 | 1264 |
| LMArena Spanish | 1336 | 1256 |
| LMArena Japanese | — | 1180 |

## Instruction Following

- Olmo 3.1 32b Instruct: 68.6 (#187)
- Qwen2.5 72B Instruct: 65.5 (#221)

| Benchmark | Olmo 3.1 32b Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1299 | 1254 |
| IFEval | — | 80.6% |

## Long Context

- Olmo 3.1 32b Instruct: 39.9 (#166)
- Qwen2.5 72B Instruct: 38.9 (#188)

| Benchmark | Olmo 3.1 32b Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1312 | 1282 |

## Writing & Preference

- Olmo 3.1 32b Instruct: 50.2 (#185)
- Qwen2.5 72B Instruct: 46.7 (#215)

| Benchmark | Olmo 3.1 32b Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1311 | 1269 |
| LMArena Creative Writing | 1264 | 1221 |
| LMArena Multi-Turn | 1309 | 1272 |
| WildBench | — | 80.2% |

## FAQ

### Is Olmo 3.1 32b Instruct better than Qwen2.5 72B Instruct?

Olmo 3.1 32b Instruct is the stronger model overall, scoring 39.4 to 31.9 on the Noometry Index.

### Is Olmo 3.1 32b Instruct or Qwen2.5 72B Instruct better for coding?

Olmo 3.1 32b Instruct scores higher on coding benchmarks: 39.5 versus 33.2 in the Noometry coding category.

### How many benchmarks do Olmo 3.1 32b Instruct and Qwen2.5 72B Instruct share?

16 benchmarks have published results for both models. Olmo 3.1 32b Instruct has 16 scored results on Noometry and Qwen2.5 72B Instruct has 43.