Model comparison
Hy3 vs Olmo 3.1 32b Instruct
Hy3 is the stronger model overall, scoring 43.6 to 38.8 on the Noometry Index.
Last verified . 15 shared benchmarks.
Tencent
Allen Institute for AI (Ai2)Summary
- They share 15 benchmarks with published results for both. Hy3 scores higher in 7 categories and Olmo 3.1 32b Instruct in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Hy3 leads 62.5 to 50.4.
Side by side
| Hy3 | Olmo 3.1 32b Instruct | |
|---|---|---|
| Provider | Tencent | Allen Institute for AI (Ai2) |
| Noometry Index | 43.6 | 38.8 |
| Released | 2026-07-06 | — |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.13 | — |
| Output $ / M tokens | $0.53 | — |
| Results tracked | 17 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.6 (#60), Olmo 3.1 32b Instruct: 38.9 (#154)
| Benchmark | Hy3 | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Coding | 1465 | 1346 |
| LMArena WebDev | 1509 | — |
Reasoning Too close to call
Hy3: 25.0 (#134), Olmo 3.1 32b Instruct: 25.4 (#131)
| Benchmark | Hy3 | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1449 | 1322 |
| NYT Connections (extended) | 41.2% | — |
Math Hy3 leads
Hy3: 37.4 (#98), Olmo 3.1 32b Instruct: 33.6 (#169)
| Benchmark | Hy3 | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Math | 1475 | 1305 |
Knowledge Hy3 leads
Hy3: 40.2 (#108), Olmo 3.1 32b Instruct: 35.4 (#175)
| Benchmark | Hy3 | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Expert | 1461 | 1307 |
Multilingual Hy3 leads
Hy3: 53.7 (#60), Olmo 3.1 32b Instruct: 42.8 (#185)
| Benchmark | Hy3 | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Non-English | 1427 | 1275 |
| LMArena Chinese | 1496 | 1304 |
| LMArena French | 1461 | 1328 |
| LMArena Korean | 1390 | 1206 |
| LMArena Russian | 1435 | 1268 |
| LMArena Spanish | 1448 | 1337 |
| LMArena German | — | 1283 |
Instruction Following Hy3 leads
Hy3: 75.3 (#68), Olmo 3.1 32b Instruct: 68.8 (#182)
| Benchmark | Hy3 | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Instruction Following | 1425 | 1298 |
Long Context Hy3 leads
Hy3: 44.1 (#70), Olmo 3.1 32b Instruct: 39.9 (#161)
| Benchmark | Hy3 | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Longer Query | 1443 | 1312 |
Writing & Preference Hy3 leads
Hy3: 62.5 (#75), Olmo 3.1 32b Instruct: 50.4 (#179)
| Benchmark | Hy3 | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Text | 1442 | 1311 |
| LMArena Creative Writing | 1399 | 1264 |
| LMArena Multi-Turn | 1436 | 1309 |
Frequently asked questions
Is Hy3 better than Olmo 3.1 32b Instruct?
Hy3 is the stronger model overall, scoring 43.6 to 38.8 on the Noometry Index.
Is Hy3 or Olmo 3.1 32b Instruct better for coding?
Hy3 scores higher on coding benchmarks: 46.6 versus 38.9 in the Noometry coding category.
How many benchmarks do Hy3 and Olmo 3.1 32b Instruct share?
15 benchmarks have published results for both models. Hy3 has 17 scored results on Noometry and Olmo 3.1 32b Instruct has 16.