Model comparison
Olmo 3 32b Think vs Qwen2.5-Max
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 38.7 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 1 category and Qwen2.5-Max in 7 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Qwen2.5-Max leads 48.1 to 41.2.
- Olmo 3 32b Think has downloadable open weights; the other is API-only.
Side by side
| Olmo 3 32b Think | Qwen2.5-Max | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | Alibaba (Qwen) |
| Noometry Index | 38.7 | 40.7 |
| Released | — | 2025-01-25 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5-Max leads
Olmo 3 32b Think: 38.6 (#172), Qwen2.5-Max: 41.8 (#117)
| Benchmark | Olmo 3 32b Think | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1319 | 1359 |
| LiveBench Coding | — | 64.4% |
Reasoning Too close to call
Olmo 3 32b Think: 25.9 (#140), Qwen2.5-Max: 25.6 (#147)
| Benchmark | Olmo 3 32b Think | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1302 | 1360 |
| LiveBench Reasoning | — | 51.4% |
| LiveBench Data Analysis | — | 67.9% |
| Epoch Capabilities Index | — | 132.53 |
| LiveBench | — | 62.3% |
Math Too close to call
Olmo 3 32b Think: 36.5 (#165), Qwen2.5-Max: 36.9 (#162)
| Benchmark | Olmo 3 32b Think | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1316 | 1369 |
| LiveBench Math | — | 58.4% |
Knowledge Too close to call
Olmo 3 32b Think: 35.0 (#190), Qwen2.5-Max: 35.3 (#186)
| Benchmark | Olmo 3 32b Think | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1273 | 1337 |
| Confabulations | — | 21.8% |
Multilingual Qwen2.5-Max leads
Olmo 3 32b Think: 41.2 (#210), Qwen2.5-Max: 48.1 (#146)
| Benchmark | Olmo 3 32b Think | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1255 | 1352 |
| LMArena Chinese | 1300 | 1382 |
| LMArena French | 1291 | 1396 |
| LMArena German | 1290 | 1350 |
| LMArena Russian | 1254 | 1353 |
| LMArena Japanese | — | 1300 |
| LMArena Korean | — | 1304 |
| LMArena Spanish | — | 1377 |
Instruction Following Qwen2.5-Max leads
Olmo 3 32b Think: 67.2 (#198), Qwen2.5-Max: 71.3 (#152)
| Benchmark | Olmo 3 32b Think | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1275 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
Long Context Qwen2.5-Max leads
Olmo 3 32b Think: 39.4 (#182), Qwen2.5-Max: 41.4 (#142)
| Benchmark | Olmo 3 32b Think | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1296 | 1358 |
Writing & Preference Qwen2.5-Max leads
Olmo 3 32b Think: 49.1 (#193), Qwen2.5-Max: 55.4 (#146)
| Benchmark | Olmo 3 32b Think | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1300 | 1367 |
| LMArena Creative Writing | 1256 | 1339 |
| LMArena Multi-Turn | 1290 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is Olmo 3 32b Think better than Qwen2.5-Max?
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 38.7 on the Noometry Index.
Is Olmo 3 32b Think or Qwen2.5-Max better for coding?
Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 38.6 in the Noometry coding category.
How many benchmarks do Olmo 3 32b Think and Qwen2.5-Max share?
14 benchmarks have published results for both models. Olmo 3 32b Think has 14 scored results on Noometry and Qwen2.5-Max has 27.