Model comparison
Hy3 vs Yi-1.5-34B
Hy3 is the stronger model overall, scoring 44.2 to 30.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
TencentSummary
- They share 17 benchmarks with published results for both. Hy3 scores higher in 8 categories and Yi-1.5-34B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Hy3 leads 40.8 to 14.8.
Side by side
| Hy3 | Yi-1.5-34B | |
|---|---|---|
| Provider | Tencent | 01.AI |
| Noometry Index | 44.2 | 30.6 |
| Released | 2026-07-06 | 2024-05-13 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.0825 | — |
| Output $ / M tokens | $0.33 | — |
| Results tracked | 19 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.8 (#63), Yi-1.5-34B: 32.4 (#272)
| Benchmark | Hy3 | Yi-1.5-34B |
|---|---|---|
| LMArena Coding | 1464 | 1169 |
| LMArena WebDev | 1508 | — |
| BigCodeBench Instruct | — | 33.9% |
| BigCodeBench Complete | — | 43.8% |
Reasoning Hy3 leads
Hy3: 26.1 (#136), Yi-1.5-34B: 22.5 (#191)
| Benchmark | Hy3 | Yi-1.5-34B |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1160 |
| NYT Connections (extended) | 41.2% | — |
Math Hy3 leads
Hy3: 40.1 (#93), Yi-1.5-34B: 27.5 (#249)
| Benchmark | Hy3 | Yi-1.5-34B |
|---|---|---|
| LMArena Math | 1475 | 1182 |
| MATH Level 5 | — | 25.5% |
Knowledge Hy3 leads
Hy3: 40.8 (#114), Yi-1.5-34B: 14.8 (#295)
| Benchmark | Hy3 | Yi-1.5-34B |
|---|---|---|
| LMArena Expert | 1460 | 1144 |
| GPQA Diamond | — | 32% |
Multilingual Hy3 leads
Hy3: 53.5 (#65), Yi-1.5-34B: 32.3 (#256)
| Benchmark | Hy3 | Yi-1.5-34B |
|---|---|---|
| LMArena Non-English | 1426 | 1121 |
| LMArena Chinese | 1493 | 1213 |
| LMArena French | 1461 | 1156 |
| LMArena German | 1439 | 1111 |
| LMArena Japanese | 1392 | 1021 |
| LMArena Korean | 1395 | 1005 |
| LMArena Russian | 1432 | 1091 |
| LMArena Spanish | 1456 | 1121 |
Instruction Following Hy3 leads
Hy3: 75.1 (#70), Yi-1.5-34B: 59.2 (#257)
| Benchmark | Hy3 | Yi-1.5-34B |
|---|---|---|
| LMArena Instruction Following | 1426 | 1139 |
Long Context Hy3 leads
Hy3: 44.1 (#75), Yi-1.5-34B: 34.6 (#248)
| Benchmark | Hy3 | Yi-1.5-34B |
|---|---|---|
| LMArena Longer Query | 1442 | 1143 |
Writing & Preference Hy3 leads
Hy3: 62.2 (#81), Yi-1.5-34B: 37.4 (#257)
| Benchmark | Hy3 | Yi-1.5-34B |
|---|---|---|
| LMArena Text | 1439 | 1173 |
| LMArena Creative Writing | 1402 | 1135 |
| LMArena Multi-Turn | 1436 | 1153 |
Frequently asked questions
Is Hy3 better than Yi-1.5-34B?
Hy3 is the stronger model overall, scoring 44.2 to 30.6 on the Noometry Index.
Is Hy3 or Yi-1.5-34B better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 32.4 in the Noometry coding category.
How many benchmarks do Hy3 and Yi-1.5-34B share?
17 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Yi-1.5-34B has 21.