Model comparison
Olmo 2 0325 32b Instruct vs Qwen3.5 35B-A3B
Qwen3.5 35B-A3B is the stronger model overall, scoring 42.0 to 32.7 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 Qwen3.5 35B-A3B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.5 35B-A3B leads 47.8 to 19.5.
Side by side
| Olmo 2 0325 32b Instruct | Qwen3.5 35B-A3B | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | Alibaba (Qwen) |
| Noometry Index | 32.7 | 42.0 |
| Released | — | 2026-02-01 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $2 |
| Results tracked | 16 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Olmo 2 0325 32b Instruct leads
Olmo 2 0325 32b Instruct: 35.2 (#227), Qwen3.5 35B-A3B: 33.8 (#251)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Coding | 1210 | 1410 |
| LMArena WebDev | — | 1254 |
| SciCode | — | 29.3% |
Reasoning Too close to call
Olmo 2 0325 32b Instruct: 23.6 (#175), Qwen3.5 35B-A3B: 24.6 (#161)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Hard Prompts | 1208 | 1400 |
| CritPt | — | 0.6% |
| Chess Puzzles | — | 10% |
| DTBench | — | 80% |
| LMCA | — | 29.5% |
| Epoch Capabilities Index | — | 142.52 |
Math Qwen3.5 35B-A3B leads
Olmo 2 0325 32b Instruct: 26.8 (#255), Qwen3.5 35B-A3B: 39.9 (#97)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Math | 1208 | 1404 |
| MathArena Final-Answer Competitions | — | 56% |
| OTIS Mock AIME 2024-2025 | — | 70% |
| Omni-MATH | 16.1% | — |
Knowledge Qwen3.5 35B-A3B leads
Olmo 2 0325 32b Instruct: 19.5 (#279), Qwen3.5 35B-A3B: 47.8 (#79)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen3.5 35B-A3B |
|---|---|---|
| GPQA Diamond | — | 83.5% |
| MMLU-Pro | 41.4% | — |
| Vectara Hallucination Rate | — | 10.5% |
| GPQA (HELM) | 28.7% | — |
| LMArena Expert | — | 1408 |
Multilingual Qwen3.5 35B-A3B leads
Olmo 2 0325 32b Instruct: 34.8 (#248), Qwen3.5 35B-A3B: 50.0 (#127)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Non-English | 1160 | 1378 |
| LMArena Chinese | 1192 | 1457 |
| LMArena Russian | 1187 | 1376 |
| LMArena French | — | 1412 |
| LMArena German | — | 1367 |
| LMArena Japanese | — | 1325 |
| LMArena Korean | — | 1356 |
| LMArena Spanish | — | 1392 |
Instruction Following Qwen3.5 35B-A3B leads
Olmo 2 0325 32b Instruct: 61.5 (#244), Qwen3.5 35B-A3B: 72.8 (#128)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Instruction Following | 1186 | 1379 |
| IFEval | 78% | — |
Long Context Qwen3.5 35B-A3B leads
Olmo 2 0325 32b Instruct: 36.2 (#234), Qwen3.5 35B-A3B: 42.4 (#127)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Longer Query | 1194 | 1389 |
Writing & Preference Qwen3.5 35B-A3B leads
Olmo 2 0325 32b Instruct: 42.1 (#236), Qwen3.5 35B-A3B: 57.9 (#124)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Text | 1218 | 1395 |
| LMArena Creative Writing | 1199 | 1346 |
| LMArena Multi-Turn | 1221 | 1390 |
| WildBench | 73.4% | — |
Frequently asked questions
Is Olmo 2 0325 32b Instruct better than Qwen3.5 35B-A3B?
Qwen3.5 35B-A3B is the stronger model overall, scoring 42.0 to 32.7 on the Noometry Index.
Is Olmo 2 0325 32b Instruct or Qwen3.5 35B-A3B better for coding?
Olmo 2 0325 32b Instruct scores higher on coding benchmarks: 35.2 versus 33.8 in the Noometry coding category.
How many benchmarks do Olmo 2 0325 32b Instruct and Qwen3.5 35B-A3B share?
11 benchmarks have published results for both models. Olmo 2 0325 32b Instruct has 16 scored results on Noometry and Qwen3.5 35B-A3B has 28.