Model comparison
Molmo 2 8b vs Qwen3.8 27B
Qwen3.8 27B is the stronger model overall, scoring 45.3 to 38.7 on the Noometry Index.
Last verified . 5 shared benchmarks.
Allen Institute for AI (Ai2)
Alibaba (Qwen)Summary
- They share 5 benchmarks with published results for both. Molmo 2 8b scores higher in 0 categories and Qwen3.8 27B in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.8 27B leads 65.9 to 49.5.
Side by side
| Molmo 2 8b | Qwen3.8 27B | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | Alibaba (Qwen) |
| Noometry Index | 38.7 | 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 | 5 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Molmo 2 8b: —, Qwen3.8 27B: 50.3 (#42)
| Benchmark | Molmo 2 8b | Qwen3.8 27B |
|---|---|---|
| LMArena WebDev | — | 1592 |
| SciCode | — | 46.6% |
| LMArena Coding | — | 1487 |
Reasoning Qwen3.8 27B leads
Molmo 2 8b: 24.5 (#146), Qwen3.8 27B: 31.5 (#71)
| Benchmark | Molmo 2 8b | Qwen3.8 27B |
|---|---|---|
| LMArena Hard Prompts | 1288 | 1459 |
| NYT Connections (extended) | — | 54.5% |
| CritPt | — | 5.4% |
| DTBench | — | 88% |
| LMCA | — | 41.4% |
| Surface Evolver Bench | — | 45% |
| Epoch Capabilities Index | — | 149.38 |
Math Not comparable
Molmo 2 8b: —, Qwen3.8 27B: 35.7 (#139)
| Benchmark | Molmo 2 8b | Qwen3.8 27B |
|---|---|---|
| ProofBench | — | 16% |
| LMArena Math | — | 1453 |
Knowledge Not comparable
Molmo 2 8b: —, Qwen3.8 27B: 40.9 (#105)
| Benchmark | Molmo 2 8b | Qwen3.8 27B |
|---|---|---|
| LMArena Expert | — | 1482 |
Multimodal Qwen3.8 27B leads
Molmo 2 8b: 29.5 (#106), Qwen3.8 27B: 40.5 (#36)
| Benchmark | Molmo 2 8b | Qwen3.8 27B |
|---|---|---|
| LMArena Vision | 1081 | 1270 |
Multilingual Qwen3.8 27B leads
Molmo 2 8b: 42.8 (#186), Qwen3.8 27B: 54.0 (#54)
| Benchmark | Molmo 2 8b | Qwen3.8 27B |
|---|---|---|
| LMArena Non-English | 1275 | 1431 |
| LMArena Chinese | — | 1504 |
| LMArena French | — | 1468 |
| LMArena German | — | 1435 |
| LMArena Japanese | — | 1392 |
| LMArena Korean | — | 1389 |
| LMArena Russian | — | 1421 |
| LMArena Spanish | — | 1444 |
Instruction Following Qwen3.8 27B leads
Molmo 2 8b: 67.2 (#196), Qwen3.8 27B: 75.8 (#54)
| Benchmark | Molmo 2 8b | Qwen3.8 27B |
|---|---|---|
| LMArena Instruction Following | 1270 | 1436 |
Long Context Not comparable
Molmo 2 8b: —, Qwen3.8 27B: 44.3 (#66)
| Benchmark | Molmo 2 8b | Qwen3.8 27B |
|---|---|---|
| LMArena Longer Query | — | 1448 |
Writing & Preference Qwen3.8 27B leads
Molmo 2 8b: 49.5 (#187), Qwen3.8 27B: 65.9 (#41)
| Benchmark | Molmo 2 8b | Qwen3.8 27B |
|---|---|---|
| LMArena Text | 1288 | 1441 |
| LMArena Creative Writing | — | 1382 |
| EQ-Bench Creative Writing | — | 1671 |
| LMArena Multi-Turn | — | 1443 |
Frequently asked questions
Is Molmo 2 8b better than Qwen3.8 27B?
Qwen3.8 27B is the stronger model overall, scoring 45.3 to 38.7 on the Noometry Index.
How many benchmarks do Molmo 2 8b and Qwen3.8 27B share?
5 benchmarks have published results for both models. Molmo 2 8b has 5 scored results on Noometry and Qwen3.8 27B has 28.