Model comparison
Hy3 vs Olmo 2 0325 32b Instruct
Hy3 is the stronger model overall, scoring 44.2 to 32.7 on the Noometry Index.
Last verified . 11 shared benchmarks.
Tencent
Allen Institute for AI (Ai2)Summary
- They share 11 benchmarks with published results for both. Hy3 scores higher in 8 categories and Olmo 2 0325 32b Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Hy3 leads 40.8 to 19.5.
Side by side
| Hy3 | Olmo 2 0325 32b Instruct | |
|---|---|---|
| Provider | Tencent | Allen Institute for AI (Ai2) |
| Noometry Index | 44.2 | 32.7 |
| Released | 2026-07-06 | — |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.0825 | — |
| Output $ / M tokens | $0.33 | — |
| Results tracked | 19 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.8 (#63), Olmo 2 0325 32b Instruct: 35.2 (#227)
| Benchmark | Hy3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Coding | 1464 | 1210 |
| LMArena WebDev | 1508 | — |
Reasoning Hy3 leads
Hy3: 26.1 (#136), Olmo 2 0325 32b Instruct: 23.6 (#175)
| Benchmark | Hy3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1208 |
| NYT Connections (extended) | 41.2% | — |
Math Hy3 leads
Hy3: 40.1 (#93), Olmo 2 0325 32b Instruct: 26.8 (#255)
| Benchmark | Hy3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Math | 1475 | 1208 |
| Omni-MATH | — | 16.1% |
Knowledge Hy3 leads
Hy3: 40.8 (#114), Olmo 2 0325 32b Instruct: 19.5 (#279)
| Benchmark | Hy3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| MMLU-Pro | — | 41.4% |
| GPQA (HELM) | — | 28.7% |
| LMArena Expert | 1460 | — |
Multilingual Hy3 leads
Hy3: 53.5 (#65), Olmo 2 0325 32b Instruct: 34.8 (#248)
| Benchmark | Hy3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Non-English | 1426 | 1160 |
| LMArena Chinese | 1493 | 1192 |
| LMArena Russian | 1432 | 1187 |
| LMArena French | 1461 | — |
| LMArena German | 1439 | — |
| LMArena Japanese | 1392 | — |
| LMArena Korean | 1395 | — |
| LMArena Spanish | 1456 | — |
Instruction Following Hy3 leads
Hy3: 75.1 (#70), Olmo 2 0325 32b Instruct: 61.5 (#244)
| Benchmark | Hy3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Instruction Following | 1426 | 1186 |
| IFEval | — | 78% |
Long Context Hy3 leads
Hy3: 44.1 (#75), Olmo 2 0325 32b Instruct: 36.2 (#234)
| Benchmark | Hy3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Longer Query | 1442 | 1194 |
Writing & Preference Hy3 leads
Hy3: 62.2 (#81), Olmo 2 0325 32b Instruct: 42.1 (#236)
| Benchmark | Hy3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Text | 1439 | 1218 |
| LMArena Creative Writing | 1402 | 1199 |
| LMArena Multi-Turn | 1436 | 1221 |
| WildBench | — | 73.4% |
Frequently asked questions
Is Hy3 better than Olmo 2 0325 32b Instruct?
Hy3 is the stronger model overall, scoring 44.2 to 32.7 on the Noometry Index.
Is Hy3 or Olmo 2 0325 32b Instruct better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 35.2 in the Noometry coding category.
How many benchmarks do Hy3 and Olmo 2 0325 32b Instruct share?
11 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Olmo 2 0325 32b Instruct has 16.