Model comparison
Hy4 preview vs Molmo 2 8b
Hy4 preview is the stronger model overall, scoring 45.3 to 39.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
Summary
- The widest gap is in reasoning, where Hy4 preview leads 31.9 to 25.6.
Side by side
| Hy4 preview | Molmo 2 8b | |
|---|---|---|
| Provider | Tencent | Allen Institute for AI (Ai2) |
| Noometry Index | 45.3 | 39.1 |
| Released | 2026-08-28 | — |
| Weights | Open | Open |
| Context window | 1.05M | — |
| Max output | 64K | — |
| Input $ / M tokens | $0.75 | — |
| Output $ / M tokens | $2.25 | — |
| Results tracked | 3 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Hy4 preview: 51.6 (#38), Molmo 2 8b: —
| Benchmark | Hy4 preview | Molmo 2 8b |
|---|---|---|
| LMArena WebDev | 1632 | — |
Reasoning Hy4 preview leads
Hy4 preview: 31.9 (#79), Molmo 2 8b: 25.6 (#146)
| Benchmark | Hy4 preview | Molmo 2 8b |
|---|---|---|
| NYT Connections (extended) | 68.2% | — |
| LMArena Hard Prompts | — | 1287 |
Math Not comparable
Hy4 preview: 55.7 (#42), Molmo 2 8b: —
| Benchmark | Hy4 preview | Molmo 2 8b |
|---|---|---|
| ProofBench | 75% | — |
Multimodal Not comparable
Hy4 preview: —, Molmo 2 8b: 30.2 (#112)
| Benchmark | Hy4 preview | Molmo 2 8b |
|---|---|---|
| LMArena Vision | — | 1081 |
Multilingual Not comparable
Hy4 preview: —, Molmo 2 8b: 42.7 (#190)
| Benchmark | Hy4 preview | Molmo 2 8b |
|---|---|---|
| LMArena Non-English | — | 1276 |
Instruction Following Not comparable
Hy4 preview: —, Molmo 2 8b: 67.0 (#201)
| Benchmark | Hy4 preview | Molmo 2 8b |
|---|---|---|
| LMArena Instruction Following | — | 1270 |
Writing & Preference Not comparable
Hy4 preview: —, Molmo 2 8b: 49.4 (#191)
| Benchmark | Hy4 preview | Molmo 2 8b |
|---|---|---|
| LMArena Text | — | 1288 |
Frequently asked questions
Is Hy4 preview better than Molmo 2 8b?
Hy4 preview is the stronger model overall, scoring 45.3 to 39.1 on the Noometry Index.
How many benchmarks do Hy4 preview and Molmo 2 8b share?
0 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and Molmo 2 8b has 5.