Model comparison
Olmo 3.1 32b Instruct vs Qwen3.8 27B
Qwen3.8 27B is the stronger model overall, scoring 45.3 to 38.8 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 3.1 32b Instruct scores higher in 0 categories and Qwen3.8 27B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.8 27B leads 65.9 to 50.4.
Side by side
| Olmo 3.1 32b Instruct | Qwen3.8 27B | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | Alibaba (Qwen) |
| Noometry Index | 38.8 | 45.3 |
| Released | — | 2026-08-14 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.99 |
| Output $ / M tokens | — | $1.49 |
| Results tracked | 16 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 27B leads
Olmo 3.1 32b Instruct: 38.9 (#154), Qwen3.8 27B: 50.3 (#42)
| Benchmark | Olmo 3.1 32b Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Coding | 1346 | 1487 |
| LMArena WebDev | — | 1592 |
| SciCode | — | 46.6% |
Reasoning Qwen3.8 27B leads
Olmo 3.1 32b Instruct: 25.4 (#131), Qwen3.8 27B: 31.5 (#71)
| Benchmark | Olmo 3.1 32b Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Hard Prompts | 1322 | 1459 |
| NYT Connections (extended) | — | 54.5% |
| CritPt | — | 5.4% |
| DTBench | — | 88% |
| LMCA | — | 41.4% |
| Surface Evolver Bench | — | 45% |
| Epoch Capabilities Index | — | 149.38 |
Math Qwen3.8 27B leads
Olmo 3.1 32b Instruct: 33.6 (#169), Qwen3.8 27B: 35.7 (#139)
| Benchmark | Olmo 3.1 32b Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Math | 1305 | 1453 |
| ProofBench | — | 16% |
Knowledge Qwen3.8 27B leads
Olmo 3.1 32b Instruct: 35.4 (#175), Qwen3.8 27B: 40.9 (#105)
| Benchmark | Olmo 3.1 32b Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Expert | 1307 | 1482 |
Multimodal Not comparable
Olmo 3.1 32b Instruct: —, Qwen3.8 27B: 40.5 (#36)
| Benchmark | Olmo 3.1 32b Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Vision | — | 1270 |
Multilingual Qwen3.8 27B leads
Olmo 3.1 32b Instruct: 42.8 (#185), Qwen3.8 27B: 54.0 (#54)
| Benchmark | Olmo 3.1 32b Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Non-English | 1275 | 1431 |
| LMArena Chinese | 1304 | 1504 |
| LMArena French | 1328 | 1468 |
| LMArena German | 1283 | 1435 |
| LMArena Korean | 1206 | 1389 |
| LMArena Russian | 1268 | 1421 |
| LMArena Spanish | 1337 | 1444 |
| LMArena Japanese | — | 1392 |
Instruction Following Qwen3.8 27B leads
Olmo 3.1 32b Instruct: 68.8 (#182), Qwen3.8 27B: 75.8 (#54)
| Benchmark | Olmo 3.1 32b Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Instruction Following | 1298 | 1436 |
Long Context Qwen3.8 27B leads
Olmo 3.1 32b Instruct: 39.9 (#161), Qwen3.8 27B: 44.3 (#66)
| Benchmark | Olmo 3.1 32b Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Longer Query | 1312 | 1448 |
Writing & Preference Qwen3.8 27B leads
Olmo 3.1 32b Instruct: 50.4 (#179), Qwen3.8 27B: 65.9 (#41)
| Benchmark | Olmo 3.1 32b Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Text | 1311 | 1441 |
| LMArena Creative Writing | 1264 | 1382 |
| LMArena Multi-Turn | 1309 | 1443 |
| EQ-Bench Creative Writing | — | 1671 |
Frequently asked questions
Is Olmo 3.1 32b Instruct better than Qwen3.8 27B?
Qwen3.8 27B is the stronger model overall, scoring 45.3 to 38.8 on the Noometry Index.
Is Olmo 3.1 32b Instruct or Qwen3.8 27B better for coding?
Qwen3.8 27B scores higher on coding benchmarks: 50.3 versus 38.9 in the Noometry coding category.
How many benchmarks do Olmo 3.1 32b Instruct and Qwen3.8 27B share?
16 benchmarks have published results for both models. Olmo 3.1 32b Instruct has 16 scored results on Noometry and Qwen3.8 27B has 28.