Model comparison
Olmo 2 0325 32b Instruct vs Qwen3 32B
Qwen3 32B is the stronger model overall, scoring 38.8 to 32.2 on the Noometry Index.
Last verified . 11 shared benchmarks.
Allen Institute for AI (Ai2)
Alibaba (Qwen)Summary
- They share 11 benchmarks with published results for both. Olmo 2 0325 32b Instruct scores higher in 1 category and Qwen3 32B in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 32B leads 40.0 to 19.2.
Side by side
| Olmo 2 0325 32b Instruct | Qwen3 32B | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | Alibaba (Qwen) |
| Noometry Index | 32.2 | 38.8 |
| Released | — | 2025-04 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $2.80 |
| Results tracked | 16 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 32B leads
Olmo 2 0325 32b Instruct: 34.6 (#222), Qwen3 32B: 37.3 (#184)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen3 32B |
|---|---|---|
| LMArena Coding | 1210 | 1358 |
| Aider Polyglot | — | 40% |
| SciCode | — | 35.4% |
Agentic & Tool Use Not comparable
Olmo 2 0325 32b Instruct: —, Qwen3 32B: 32.3 (#58)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 48.7% |
Reasoning Olmo 2 0325 32b Instruct leads
Olmo 2 0325 32b Instruct: 22.6 (#174), Qwen3 32B: 19.6 (#233)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen3 32B |
|---|---|---|
| LMArena Hard Prompts | 1208 | 1335 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 5% |
| DTBench | — | 67.5% |
| LMCA | — | 17.3% |
| Epoch Capabilities Index | — | 138.51 |
Math Qwen3 32B leads
Olmo 2 0325 32b Instruct: 24.8 (#255), Qwen3 32B: 37.9 (#89)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen3 32B |
|---|---|---|
| LMArena Math | 1208 | 1399 |
| OTIS Mock AIME 2024-2025 | — | 66.9% |
| Omni-MATH | 16.1% | — |
Knowledge Qwen3 32B leads
Olmo 2 0325 32b Instruct: 19.2 (#274), Qwen3 32B: 40.0 (#112)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen3 32B |
|---|---|---|
| GPQA Diamond | — | 65.7% |
| MMLU-Pro | 41.4% | — |
| Vectara Hallucination Rate | — | 5.9% |
| GPQA (HELM) | 28.7% | — |
| LMArena Expert | — | 1362 |
Multilingual Qwen3 32B leads
Olmo 2 0325 32b Instruct: 35.0 (#243), Qwen3 32B: 45.8 (#162)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 1160 | 1317 |
| LMArena Chinese | 1192 | 1357 |
| LMArena Russian | 1187 | 1311 |
| LMArena German | — | 1341 |
Instruction Following Qwen3 32B leads
Olmo 2 0325 32b Instruct: 61.8 (#238), Qwen3 32B: 69.1 (#174)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 1186 | 1305 |
| IFEval | 78% | — |
Long Context Qwen3 32B leads
Olmo 2 0325 32b Instruct: 36.2 (#229), Qwen3 32B: 43.7 (#83)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen3 32B |
|---|---|---|
| LMArena Longer Query | 1194 | 1327 |
| Fiction.LiveBench | — | 74.2% |
Writing & Preference Qwen3 32B leads
Olmo 2 0325 32b Instruct: 42.3 (#231), Qwen3 32B: 53.1 (#158)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen3 32B |
|---|---|---|
| LMArena Text | 1218 | 1340 |
| LMArena Creative Writing | 1199 | 1297 |
| LMArena Multi-Turn | 1221 | 1331 |
| WildBench | 73.4% | — |
Frequently asked questions
Is Olmo 2 0325 32b Instruct better than Qwen3 32B?
Qwen3 32B is the stronger model overall, scoring 38.8 to 32.2 on the Noometry Index.
Is Olmo 2 0325 32b Instruct or Qwen3 32B better for coding?
Qwen3 32B scores higher on coding benchmarks: 37.3 versus 34.6 in the Noometry coding category.
How many benchmarks do Olmo 2 0325 32b Instruct and Qwen3 32B share?
11 benchmarks have published results for both models. Olmo 2 0325 32b Instruct has 16 scored results on Noometry and Qwen3 32B has 26.