Model comparison
Molmo 2 8b vs Qwen2-72B
Molmo 2 8b is the stronger model overall, scoring 38.7 to 29.5 on the Noometry Index.
Last verified . 4 shared benchmarks.
Allen Institute for AI (Ai2)
Alibaba (Qwen)Summary
- They share 4 benchmarks with published results for both. Molmo 2 8b scores higher in 4 categories and Qwen2-72B in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Molmo 2 8b leads 49.5 to 41.0.
Side by side
| Molmo 2 8b | Qwen2-72B | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | Alibaba (Qwen) |
| Noometry Index | 38.7 | 29.5 |
| Released | — | 2024-06-07 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 5 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Molmo 2 8b: —, Qwen2-72B: 28.7 (#303)
| Benchmark | Molmo 2 8b | Qwen2-72B |
|---|---|---|
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| LMArena Coding | — | 1196 |
| BigCodeBench Complete | — | 54% |
Agentic & Tool Use Not comparable
Molmo 2 8b: —, Qwen2-72B: 16.9 (#138)
| Benchmark | Molmo 2 8b | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Molmo 2 8b leads
Molmo 2 8b: 24.5 (#146), Qwen2-72B: 22.2 (#184)
| Benchmark | Molmo 2 8b | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1288 | 1191 |
| Epoch Capabilities Index | — | 125.27 |
Math Not comparable
Molmo 2 8b: —, Qwen2-72B: 27.9 (#232)
| Benchmark | Molmo 2 8b | Qwen2-72B |
|---|---|---|
| LMArena Math | — | 1235 |
| MATH Level 5 | — | 39.1% |
Knowledge Not comparable
Molmo 2 8b: —, Qwen2-72B: 21.2 (#270)
| Benchmark | Molmo 2 8b | Qwen2-72B |
|---|---|---|
| GPQA Diamond | — | 40.8% |
| LMArena Expert | — | 1171 |
| MMLU | — | 82.4% |
Multimodal Not comparable
Molmo 2 8b: 29.5 (#106), Qwen2-72B: —
| Benchmark | Molmo 2 8b | Qwen2-72B |
|---|---|---|
| LMArena Vision | 1081 | — |
Multilingual Molmo 2 8b leads
Molmo 2 8b: 42.8 (#186), Qwen2-72B: 36.0 (#239)
| Benchmark | Molmo 2 8b | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1275 | 1176 |
| LMArena Chinese | — | 1240 |
| LMArena French | — | 1169 |
| LMArena German | — | 1151 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |
| LMArena Russian | — | 1169 |
| LMArena Spanish | — | 1168 |
Instruction Following Molmo 2 8b leads
Molmo 2 8b: 67.2 (#196), Qwen2-72B: 62.0 (#236)
| Benchmark | Molmo 2 8b | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1270 | 1181 |
Long Context Not comparable
Molmo 2 8b: —, Qwen2-72B: 36.1 (#230)
| Benchmark | Molmo 2 8b | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | — | 1193 |
Writing & Preference Molmo 2 8b leads
Molmo 2 8b: 49.5 (#187), Qwen2-72B: 41.0 (#236)
| Benchmark | Molmo 2 8b | Qwen2-72B |
|---|---|---|
| LMArena Text | 1288 | 1203 |
| LMArena Creative Writing | — | 1181 |
| LMArena Multi-Turn | — | 1195 |
Frequently asked questions
Is Molmo 2 8b better than Qwen2-72B?
Molmo 2 8b is the stronger model overall, scoring 38.7 to 29.5 on the Noometry Index.
How many benchmarks do Molmo 2 8b and Qwen2-72B share?
4 benchmarks have published results for both models. Molmo 2 8b has 5 scored results on Noometry and Qwen2-72B has 26.