Model comparison
Olmo 2 0325 32b Instruct vs Qwen3 235B-A22B
Qwen3 235B-A22B is the stronger model overall, scoring 43.2 to 32.2 on the Noometry Index.
Last verified . 16 shared benchmarks.
Allen Institute for AI (Ai2)
Alibaba (Qwen)Summary
- They share 16 benchmarks with published results for both. Olmo 2 0325 32b Instruct scores higher in 1 category and Qwen3 235B-A22B in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 235B-A22B leads 49.5 to 19.2.
- The biggest single-benchmark swing is Omni-MATH: 16.1% for Olmo 2 0325 32b Instruct and 71.8% for Qwen3 235B-A22B.
Side by side
| Olmo 2 0325 32b Instruct | Qwen3 235B-A22B | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | Alibaba (Qwen) |
| Noometry Index | 32.2 | 43.2 |
| 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 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 235B-A22B leads
Olmo 2 0325 32b Instruct: 34.6 (#222), Qwen3 235B-A22B: 43.8 (#72)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen3 235B-A22B |
|---|---|---|
| LMArena Coding | 1210 | 1445 |
| Aider Polyglot | — | 59.6% |
| SciCode | — | 42.4% |
| WeirdML | — | 41% |
Agentic & Tool Use Not comparable
Olmo 2 0325 32b Instruct: —, Qwen3 235B-A22B: 33.7 (#48)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen3 235B-A22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 52.1% |
| Vending-Bench 2 | — | -11.34 |
Reasoning Olmo 2 0325 32b Instruct leads
Olmo 2 0325 32b Instruct: 22.6 (#174), Qwen3 235B-A22B: 15.8 (#302)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen3 235B-A22B |
|---|---|---|
| LMArena Hard Prompts | 1208 | 1433 |
| ARC-AGI-2 | — | 1.3% |
| SimpleBench | — | 31% |
| Kagi LLM Benchmark | — | 69.4% |
| ARC-AGI-1 | — | 11% |
| CritPt | — | 0% |
| Chess Puzzles | — | 12% |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 80.3% |
| LMCA | — | 29.3% |
| Epoch Capabilities Index | — | 143.87 |
| ForecastBench | — | 59.7 |
Math Qwen3 235B-A22B leads
Olmo 2 0325 32b Instruct: 24.8 (#255), Qwen3 235B-A22B: 48.5 (#51)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen3 235B-A22B |
|---|---|---|
| Omni-MATH | 16.1% | 71.8% |
| LMArena Math | 1208 | 1431 |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| MATH Level 5 | — | 68.9% |
| FrontierMath (Feb 2025 set) | — | 8.5% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Qwen3 235B-A22B leads
Olmo 2 0325 32b Instruct: 19.2 (#274), Qwen3 235B-A22B: 49.5 (#67)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen3 235B-A22B |
|---|---|---|
| MMLU-Pro | 41.4% | 84.4% |
| GPQA (HELM) | 28.7% | 72.7% |
| GPQA Diamond | — | 80.1% |
| SimpleQA Verified | — | 40.4% |
| Confabulations | — | 15.6% |
| Vectara Hallucination Rate | — | 9.3% |
| LMArena Expert | — | 1460 |
Multilingual Qwen3 235B-A22B leads
Olmo 2 0325 32b Instruct: 35.0 (#243), Qwen3 235B-A22B: 52.5 (#84)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1160 | 1410 |
| LMArena Chinese | 1192 | 1481 |
| LMArena Russian | 1187 | 1411 |
| LMArena French | — | 1445 |
| LMArena German | — | 1432 |
| LMArena Japanese | — | 1400 |
| LMArena Korean | — | 1391 |
| LMArena Spanish | — | 1429 |
Instruction Following Qwen3 235B-A22B leads
Olmo 2 0325 32b Instruct: 61.8 (#238), Qwen3 235B-A22B: 72.8 (#132)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen3 235B-A22B |
|---|---|---|
| IFEval | 78% | 83.5% |
| LMArena Instruction Following | 1186 | 1408 |
Long Context Qwen3 235B-A22B leads
Olmo 2 0325 32b Instruct: 36.2 (#229), Qwen3 235B-A22B: 46.1 (#25)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen3 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1194 | 1426 |
| Fiction.LiveBench | — | 75% |
Writing & Preference Qwen3 235B-A22B leads
Olmo 2 0325 32b Instruct: 42.3 (#231), Qwen3 235B-A22B: 59.8 (#103)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1218 | 1419 |
| LMArena Creative Writing | 1199 | 1384 |
| WildBench | 73.4% | 86.6% |
| LMArena Multi-Turn | 1221 | 1432 |
| Short-Story Creative Writing | — | 83% |
| EQ-Bench Creative Writing | — | 1366 |
Frequently asked questions
Is Olmo 2 0325 32b Instruct better than Qwen3 235B-A22B?
Qwen3 235B-A22B is the stronger model overall, scoring 43.2 to 32.2 on the Noometry Index.
Is Olmo 2 0325 32b Instruct or Qwen3 235B-A22B better for coding?
Qwen3 235B-A22B scores higher on coding benchmarks: 43.8 versus 34.6 in the Noometry coding category.
How many benchmarks do Olmo 2 0325 32b Instruct and Qwen3 235B-A22B share?
16 benchmarks have published results for both models. Olmo 2 0325 32b Instruct has 16 scored results on Noometry and Qwen3 235B-A22B has 49.