Model comparison
Olmo 3 32b Think vs Qwen Max
Olmo 3 32b Think is the stronger model overall, scoring 38.7 to 34.7 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 6 categories and Qwen Max in 2 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Olmo 3 32b Think leads 36.5 to 22.3.
- Olmo 3 32b Think has downloadable open weights; the other is API-only.
Side by side
| Olmo 3 32b Think | Qwen Max | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | Alibaba (Qwen) |
| Noometry Index | 38.7 | 34.7 |
| Released | — | 2024-04-03 |
| Weights | Open | Proprietary |
| Context window | — | 33K |
| Max output | — | 8K |
| Input $ / M tokens | — | $1.60 |
| Output $ / M tokens | — | $6.40 |
| Results tracked | 14 | 23 |
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), Qwen Max: 30.7 (#292)
| Benchmark | Olmo 3 32b Think | Qwen Max |
|---|---|---|
| LMArena Coding | 1319 | 1288 |
| Aider Polyglot | — | 21.8% |
Reasoning Too close to call
Olmo 3 32b Think: 25.9 (#140), Qwen Max: 25.1 (#151)
| Benchmark | Olmo 3 32b Think | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1302 | 1269 |
Math Olmo 3 32b Think leads
Olmo 3 32b Think: 36.5 (#165), Qwen Max: 22.3 (#276)
| Benchmark | Olmo 3 32b Think | Qwen Max |
|---|---|---|
| LMArena Math | 1316 | 1275 |
| OTIS Mock AIME 2024-2025 | — | 16.1% |
| MATH Level 5 | — | 67.2% |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge Olmo 3 32b Think leads
Olmo 3 32b Think: 35.0 (#190), Qwen Max: 30.3 (#228)
| Benchmark | Olmo 3 32b Think | Qwen Max |
|---|---|---|
| LMArena Expert | 1273 | 1248 |
| GPQA Diamond | — | 56.1% |
Multilingual Too close to call
Olmo 3 32b Think: 41.2 (#210), Qwen Max: 41.8 (#202)
| Benchmark | Olmo 3 32b Think | Qwen Max |
|---|---|---|
| LMArena Non-English | 1255 | 1263 |
| LMArena Chinese | 1300 | 1254 |
| LMArena French | 1291 | 1330 |
| LMArena German | 1290 | 1254 |
| LMArena Russian | 1254 | 1274 |
| LMArena Japanese | — | 1205 |
| LMArena Korean | — | 1142 |
| LMArena Spanish | — | 1290 |
Instruction Following Too close to call
Olmo 3 32b Think: 67.2 (#198), Qwen Max: 66.5 (#208)
| Benchmark | Olmo 3 32b Think | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1275 | 1262 |
Long Context Too close to call
Olmo 3 32b Think: 39.4 (#182), Qwen Max: 39.4 (#180)
| Benchmark | Olmo 3 32b Think | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1296 | 1288 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Olmo 3 32b Think leads
Olmo 3 32b Think: 49.1 (#193), Qwen Max: 47.8 (#205)
| Benchmark | Olmo 3 32b Think | Qwen Max |
|---|---|---|
| LMArena Text | 1300 | 1282 |
| LMArena Creative Writing | 1256 | 1248 |
| LMArena Multi-Turn | 1290 | 1277 |
Frequently asked questions
Is Olmo 3 32b Think better than Qwen Max?
Olmo 3 32b Think is the stronger model overall, scoring 38.7 to 34.7 on the Noometry Index.
Is Olmo 3 32b Think or Qwen Max better for coding?
Olmo 3 32b Think scores higher on coding benchmarks: 38.6 versus 30.7 in the Noometry coding category.
How many benchmarks do Olmo 3 32b Think and Qwen Max share?
14 benchmarks have published results for both models. Olmo 3 32b Think has 14 scored results on Noometry and Qwen Max has 23.