Model comparison
Olmo 3 32b Think vs Qwen3.8 Max
Qwen3.8 Max is the stronger model overall, scoring 56.8 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 0 categories and Qwen3.8 Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.2 to 36.5.
- Olmo 3 32b Think has downloadable open weights; the other is API-only.
Side by side
| Olmo 3 32b Think | Qwen3.8 Max | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | Alibaba (Qwen) |
| Noometry Index | 38.7 | 56.8 |
| Released | — | 2026-08-02 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 131K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 14 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 Max leads
Olmo 3 32b Think: 38.6 (#172), Qwen3.8 Max: 53.5 (#29)
| Benchmark | Olmo 3 32b Think | Qwen3.8 Max |
|---|---|---|
| LMArena Coding | 1319 | 1502 |
| DeepSWE | — | 57.5% |
| LMArena WebDev | — | 1674 |
| FrontierSWE | — | 17.8% |
| SciCode | — | 53.2% |
Agentic & Tool Use Not comparable
Olmo 3 32b Think: —, Qwen3.8 Max: 45.4 (#14)
| Benchmark | Olmo 3 32b Think | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |
Reasoning Qwen3.8 Max leads
Olmo 3 32b Think: 25.9 (#140), Qwen3.8 Max: 54.4 (#26)
| Benchmark | Olmo 3 32b Think | Qwen3.8 Max |
|---|---|---|
| LMArena Hard Prompts | 1302 | 1496 |
| NYT Connections (extended) | — | 88.3% |
| CritPt | — | 20% |
| Chess Puzzles | — | 40% |
| Mystery Game Puzzles | — | 38% |
| DTBench | — | 92% |
| LMCA | — | 46.2% |
| Epoch Capabilities Index | — | 156.41 |
Math Qwen3.8 Max leads
Olmo 3 32b Think: 36.5 (#165), Qwen3.8 Max: 73.2 (#20)
| Benchmark | Olmo 3 32b Think | Qwen3.8 Max |
|---|---|---|
| LMArena Math | 1316 | 1499 |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 58% |
Knowledge Qwen3.8 Max leads
Olmo 3 32b Think: 35.0 (#190), Qwen3.8 Max: 61.7 (#27)
| Benchmark | Olmo 3 32b Think | Qwen3.8 Max |
|---|---|---|
| LMArena Expert | 1273 | 1507 |
| GPQA Diamond | — | 92.7% |
| SimpleQA Verified | — | 47.3% |
Multimodal Not comparable
Olmo 3 32b Think: —, Qwen3.8 Max: 37.2 (#75)
| Benchmark | Olmo 3 32b Think | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |
Multilingual Qwen3.8 Max leads
Olmo 3 32b Think: 41.2 (#210), Qwen3.8 Max: 56.7 (#18)
| Benchmark | Olmo 3 32b Think | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1255 | 1472 |
| LMArena Chinese | 1300 | 1538 |
| LMArena French | 1291 | 1503 |
| LMArena German | 1290 | 1483 |
| LMArena Russian | 1254 | 1481 |
| LMArena Japanese | — | 1467 |
| LMArena Korean | — | 1461 |
| LMArena Spanish | — | 1492 |
Instruction Following Qwen3.8 Max leads
Olmo 3 32b Think: 67.2 (#198), Qwen3.8 Max: 77.6 (#17)
| Benchmark | Olmo 3 32b Think | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1275 | 1479 |
Long Context Qwen3.8 Max leads
Olmo 3 32b Think: 39.4 (#182), Qwen3.8 Max: 45.6 (#31)
| Benchmark | Olmo 3 32b Think | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1296 | 1489 |
Writing & Preference Qwen3.8 Max leads
Olmo 3 32b Think: 49.1 (#193), Qwen3.8 Max: 67.1 (#30)
| Benchmark | Olmo 3 32b Think | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1300 | 1483 |
| LMArena Creative Writing | 1256 | 1479 |
| LMArena Multi-Turn | 1290 | 1489 |
Frequently asked questions
Is Olmo 3 32b Think better than Qwen3.8 Max?
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 38.7 on the Noometry Index.
Is Olmo 3 32b Think or Qwen3.8 Max better for coding?
Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 38.6 in the Noometry coding category.
How many benchmarks do Olmo 3 32b Think and Qwen3.8 Max share?
14 benchmarks have published results for both models. Olmo 3 32b Think has 14 scored results on Noometry and Qwen3.8 Max has 39.