Model comparison
Hy4 preview vs Olmo 3 32b Think
Hy4 preview is the stronger model overall, scoring 45.3 to 38.7 on the Noometry Index.
Last verified . 0 shared benchmarks.
Tencent
Allen Institute for AI (Ai2)Summary
- The widest gap is in math, where Hy4 preview leads 55.7 to 36.5.
Side by side
| Hy4 preview | Olmo 3 32b Think | |
|---|---|---|
| Provider | Tencent | Allen Institute for AI (Ai2) |
| Noometry Index | 45.3 | 38.7 |
| Released | 2026-08-28 | — |
| Weights | Open | Open |
| Context window | 1.05M | — |
| Max output | 64K | — |
| Input $ / M tokens | $0.83 | — |
| Output $ / M tokens | $2.50 | — |
| Results tracked | 3 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
Hy4 preview: 51.6 (#38), Olmo 3 32b Think: 38.6 (#172)
| Benchmark | Hy4 preview | Olmo 3 32b Think |
|---|---|---|
| LMArena WebDev | 1632 | — |
| LMArena Coding | — | 1319 |
Reasoning Hy4 preview leads
Hy4 preview: 31.9 (#79), Olmo 3 32b Think: 25.9 (#140)
| Benchmark | Hy4 preview | Olmo 3 32b Think |
|---|---|---|
| NYT Connections (extended) | 68.2% | — |
| LMArena Hard Prompts | — | 1302 |
Math Hy4 preview leads
Hy4 preview: 55.7 (#42), Olmo 3 32b Think: 36.5 (#165)
| Benchmark | Hy4 preview | Olmo 3 32b Think |
|---|---|---|
| ProofBench | 75% | — |
| LMArena Math | — | 1316 |
Knowledge Not comparable
Hy4 preview: —, Olmo 3 32b Think: 35.0 (#190)
| Benchmark | Hy4 preview | Olmo 3 32b Think |
|---|---|---|
| LMArena Expert | — | 1273 |
Multilingual Not comparable
Hy4 preview: —, Olmo 3 32b Think: 41.2 (#210)
| Benchmark | Hy4 preview | Olmo 3 32b Think |
|---|---|---|
| LMArena Non-English | — | 1255 |
| LMArena Chinese | — | 1300 |
| LMArena French | — | 1291 |
| LMArena German | — | 1290 |
| LMArena Russian | — | 1254 |
Instruction Following Not comparable
Hy4 preview: —, Olmo 3 32b Think: 67.2 (#198)
| Benchmark | Hy4 preview | Olmo 3 32b Think |
|---|---|---|
| LMArena Instruction Following | — | 1275 |
Long Context Not comparable
Hy4 preview: —, Olmo 3 32b Think: 39.4 (#182)
| Benchmark | Hy4 preview | Olmo 3 32b Think |
|---|---|---|
| LMArena Longer Query | — | 1296 |
Writing & Preference Not comparable
Hy4 preview: —, Olmo 3 32b Think: 49.1 (#193)
| Benchmark | Hy4 preview | Olmo 3 32b Think |
|---|---|---|
| LMArena Text | — | 1300 |
| LMArena Creative Writing | — | 1256 |
| LMArena Multi-Turn | — | 1290 |
Frequently asked questions
Is Hy4 preview better than Olmo 3 32b Think?
Hy4 preview is the stronger model overall, scoring 45.3 to 38.7 on the Noometry Index.
Is Hy4 preview or Olmo 3 32b Think better for coding?
Hy4 preview scores higher on coding benchmarks: 51.6 versus 38.6 in the Noometry coding category.
How many benchmarks do Hy4 preview and Olmo 3 32b Think share?
0 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and Olmo 3 32b Think has 14.