Model comparison
Molmo 2 8b vs Qwen3.5 27B
Qwen3.5 27B is the stronger model overall, scoring 41.4 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 Qwen3.5 27B in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.5 27B leads 59.5 to 49.5.
Side by side
| Molmo 2 8b | Qwen3.5 27B | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | Alibaba (Qwen) |
| Noometry Index | 38.7 | 41.4 |
| Released | — | 2026-02-23 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $2.40 |
| 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: —, Qwen3.5 27B: 38.6 (#159)
| Benchmark | Molmo 2 8b | Qwen3.5 27B |
|---|---|---|
| LMArena WebDev | — | 1357 |
| WeirdML | — | 39.5% |
| LMArena Coding | — | 1427 |
| ALE-Bench | — | 349.45 |
Agentic & Tool Use Not comparable
Molmo 2 8b: —, Qwen3.5 27B: —
| Benchmark | Molmo 2 8b | Qwen3.5 27B |
|---|---|---|
| Vending-Bench 2 | — | 201.98 |
Reasoning Qwen3.5 27B leads
Molmo 2 8b: 24.5 (#146), Qwen3.5 27B: 26.6 (#116)
| Benchmark | Molmo 2 8b | Qwen3.5 27B |
|---|---|---|
| LMArena Hard Prompts | 1288 | 1414 |
| NYT Connections (extended) | — | 47.9% |
| Thematic Generalization | — | 45.5% |
| DTBench | — | 82.4% |
| LMCA | — | 34% |
Math Not comparable
Molmo 2 8b: —, Qwen3.5 27B: 36.8 (#103)
| Benchmark | Molmo 2 8b | Qwen3.5 27B |
|---|---|---|
| MathArena Final-Answer Competitions | — | 56.7% |
| LMArena Math | — | 1428 |
Knowledge Not comparable
Molmo 2 8b: —, Qwen3.5 27B: 37.4 (#149)
| Benchmark | Molmo 2 8b | Qwen3.5 27B |
|---|---|---|
| Vectara Hallucination Rate | — | 12.1% |
| LMArena Expert | — | 1428 |
Multimodal Qwen3.5 27B leads
Molmo 2 8b: 29.5 (#106), Qwen3.5 27B: 38.7 (#56)
| Benchmark | Molmo 2 8b | Qwen3.5 27B |
|---|---|---|
| LMArena Vision | 1081 | 1240 |
Multilingual Qwen3.5 27B leads
Molmo 2 8b: 42.8 (#186), Qwen3.5 27B: 51.0 (#112)
| Benchmark | Molmo 2 8b | Qwen3.5 27B |
|---|---|---|
| LMArena Non-English | 1275 | 1390 |
| LMArena Chinese | — | 1478 |
| LMArena French | — | 1409 |
| LMArena German | — | 1393 |
| LMArena Japanese | — | 1345 |
| LMArena Korean | — | 1359 |
| LMArena Russian | — | 1389 |
| LMArena Spanish | — | 1408 |
Instruction Following Qwen3.5 27B leads
Molmo 2 8b: 67.2 (#196), Qwen3.5 27B: 73.7 (#114)
| Benchmark | Molmo 2 8b | Qwen3.5 27B |
|---|---|---|
| LMArena Instruction Following | 1270 | 1393 |
Long Context Not comparable
Molmo 2 8b: —, Qwen3.5 27B: 43.1 (#103)
| Benchmark | Molmo 2 8b | Qwen3.5 27B |
|---|---|---|
| LMArena Longer Query | — | 1413 |
Writing & Preference Qwen3.5 27B leads
Molmo 2 8b: 49.5 (#187), Qwen3.5 27B: 59.5 (#106)
| Benchmark | Molmo 2 8b | Qwen3.5 27B |
|---|---|---|
| LMArena Text | 1288 | 1409 |
| LMArena Creative Writing | — | 1362 |
| LMArena Multi-Turn | — | 1410 |
Frequently asked questions
Is Molmo 2 8b better than Qwen3.5 27B?
Qwen3.5 27B is the stronger model overall, scoring 41.4 to 38.7 on the Noometry Index.
How many benchmarks do Molmo 2 8b and Qwen3.5 27B share?
5 benchmarks have published results for both models. Molmo 2 8b has 5 scored results on Noometry and Qwen3.5 27B has 28.