Model comparison
Olmo 3 32b Think vs Qwen2-72B
Olmo 3 32b Think is the stronger model overall, scoring 38.7 to 30.0 on the Noometry Index.
Last verified . 14 shared benchmarks.
Allen Institute for AI (Ai2)
Alibaba (Qwen)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 35.0 to 21.2.
Side by side
| Olmo 3 32b Think | Qwen2-72B | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | Alibaba (Qwen) |
| Noometry Index | 38.7 | 30.0 |
| Released | — | 2024-06-07 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Olmo 3 32b Think leads
Olmo 3 32b Think: 38.6 (#172), Qwen2-72B: 29.1 (#310)
| Benchmark | Olmo 3 32b Think | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1319 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
Agentic & Tool Use Not comparable
Olmo 3 32b Think: —, Qwen2-72B: 17.0 (#146)
| Benchmark | Olmo 3 32b Think | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Olmo 3 32b Think leads
Olmo 3 32b Think: 25.9 (#140), Qwen2-72B: 23.2 (#181)
| Benchmark | Olmo 3 32b Think | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1302 | 1191 |
| Epoch Capabilities Index | — | 125.28 |
Math Olmo 3 32b Think leads
Olmo 3 32b Think: 36.5 (#165), Qwen2-72B: 30.2 (#236)
| Benchmark | Olmo 3 32b Think | Qwen2-72B |
|---|---|---|
| LMArena Math | 1316 | 1235 |
| MATH Level 5 | — | 39.1% |
Knowledge Olmo 3 32b Think leads
Olmo 3 32b Think: 35.0 (#190), Qwen2-72B: 21.2 (#275)
| Benchmark | Olmo 3 32b Think | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1273 | 1171 |
| GPQA Diamond | — | 40.8% |
| MMLU | — | 82.4% |
Multilingual Olmo 3 32b Think leads
Olmo 3 32b Think: 41.2 (#210), Qwen2-72B: 35.9 (#244)
| Benchmark | Olmo 3 32b Think | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1255 | 1176 |
| LMArena Chinese | 1300 | 1240 |
| LMArena French | 1291 | 1170 |
| LMArena German | 1290 | 1151 |
| LMArena Russian | 1254 | 1169 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |
| LMArena Spanish | — | 1169 |
Instruction Following Olmo 3 32b Think leads
Olmo 3 32b Think: 67.2 (#198), Qwen2-72B: 61.7 (#241)
| Benchmark | Olmo 3 32b Think | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1275 | 1181 |
Long Context Olmo 3 32b Think leads
Olmo 3 32b Think: 39.4 (#182), Qwen2-72B: 36.1 (#235)
| Benchmark | Olmo 3 32b Think | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1296 | 1192 |
Writing & Preference Olmo 3 32b Think leads
Olmo 3 32b Think: 49.1 (#193), Qwen2-72B: 40.8 (#241)
| Benchmark | Olmo 3 32b Think | Qwen2-72B |
|---|---|---|
| LMArena Text | 1300 | 1203 |
| LMArena Creative Writing | 1256 | 1181 |
| LMArena Multi-Turn | 1290 | 1196 |
Frequently asked questions
Is Olmo 3 32b Think better than Qwen2-72B?
Olmo 3 32b Think is the stronger model overall, scoring 38.7 to 30.0 on the Noometry Index.
Is Olmo 3 32b Think or Qwen2-72B better for coding?
Olmo 3 32b Think scores higher on coding benchmarks: 38.6 versus 29.1 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.