# Olmo 3 32b Think vs Qwen2-72B

> Olmo 3 32b Think is the stronger model overall, scoring 38.1 to 29.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/olmo-3-32b-think-vs-qwen2-72b
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. Olmo 3 32b Think scores higher in 8 categories and Qwen2-72B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Olmo 3 32b Think leads 34.4 to 21.2.

## Snapshot

| | Olmo 3 32b Think | Qwen2-72B |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | Alibaba (Qwen) |
| Noometry Index | 38.1 | 29.5 |
| Rank | 182 | 294 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Olmo 3 32b Think: 38.0 (#169)
- Qwen2-72B: 28.7 (#303)

| Benchmark | Olmo 3 32b Think | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1318 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |

## Agentic & Tool Use

- Olmo 3 32b Think: —
- Qwen2-72B: 16.9 (#138)

| Benchmark | Olmo 3 32b Think | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |

## Reasoning

- Olmo 3 32b Think: 24.9 (#138)
- Qwen2-72B: 22.2 (#184)

| Benchmark | Olmo 3 32b Think | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1302 | 1191 |
| Epoch Capabilities Index | — | 125.27 |

## Math

- Olmo 3 32b Think: 33.8 (#165)
- Qwen2-72B: 27.9 (#232)

| Benchmark | Olmo 3 32b Think | Qwen2-72B |
|---|---|---|
| LMArena Math | 1315 | 1235 |
| MATH Level 5 | — | 39.1% |

## Knowledge

- Olmo 3 32b Think: 34.4 (#189)
- Qwen2-72B: 21.2 (#270)

| Benchmark | Olmo 3 32b Think | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1272 | 1171 |
| GPQA Diamond | — | 40.8% |
| MMLU | — | 82.4% |

## Multilingual

- Olmo 3 32b Think: 41.4 (#205)
- Qwen2-72B: 36.0 (#239)

| Benchmark | Olmo 3 32b Think | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1255 | 1176 |
| LMArena Chinese | 1300 | 1240 |
| LMArena French | 1291 | 1169 |
| LMArena German | 1290 | 1151 |
| LMArena Russian | 1255 | 1169 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |
| LMArena Spanish | — | 1168 |

## Instruction Following

- Olmo 3 32b Think: 67.4 (#193)
- Qwen2-72B: 62.0 (#236)

| Benchmark | Olmo 3 32b Think | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1275 | 1181 |

## Long Context

- Olmo 3 32b Think: 39.4 (#177)
- Qwen2-72B: 36.1 (#230)

| Benchmark | Olmo 3 32b Think | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1296 | 1193 |

## Writing & Preference

- Olmo 3 32b Think: 49.2 (#188)
- Qwen2-72B: 41.0 (#236)

| Benchmark | Olmo 3 32b Think | Qwen2-72B |
|---|---|---|
| LMArena Text | 1300 | 1203 |
| LMArena Creative Writing | 1256 | 1181 |
| LMArena Multi-Turn | 1289 | 1195 |

## FAQ

### Is Olmo 3 32b Think better than Qwen2-72B?

Olmo 3 32b Think is the stronger model overall, scoring 38.1 to 29.5 on the Noometry Index.

### Is Olmo 3 32b Think or Qwen2-72B better for coding?

Olmo 3 32b Think scores higher on coding benchmarks: 38.0 versus 28.7 in the Noometry coding category.

### How many benchmarks do Olmo 3 32b Think and Qwen2-72B share?

14 benchmarks have published results for both models. Olmo 3 32b Think has 14 scored results on Noometry and Qwen2-72B has 26.