Model comparison
Dolly 2.0-12b vs Hy3
Hy3 is the stronger model overall, scoring 44.2 to 25.5 on the Noometry Index.
Last verified . 9 shared benchmarks.
Databricks
TencentSummary
- They share 9 benchmarks with published results for both. Dolly 2.0-12b scores higher in 0 categories and Hy3 in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Hy3 leads 62.2 to 15.2.
Side by side
| Dolly 2.0-12b | Hy3 | |
|---|---|---|
| Provider | Databricks | Tencent |
| Noometry Index | 25.5 | 44.2 |
| Released | 2023-04-11 | 2026-07-06 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.0825 |
| Output $ / M tokens | — | $0.33 |
| Results tracked | 17 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Dolly 2.0-12b: 23.4 (#332), Hy3: 46.8 (#63)
| Benchmark | Dolly 2.0-12b | Hy3 |
|---|---|---|
| LMArena Coding | 776 | 1464 |
| LMArena WebDev | — | 1508 |
Reasoning Hy3 leads
Dolly 2.0-12b: 15.3 (#316), Hy3: 26.1 (#136)
| Benchmark | Dolly 2.0-12b | Hy3 |
|---|---|---|
| LMArena Hard Prompts | 804 | 1447 |
| NYT Connections (extended) | — | 41.2% |
| Epoch Capabilities Index | 89.67 | — |
| HellaSwag | 70.8% | — |
| PIQA | 75.4% | — |
| WinoGrande | 61.8% | — |
Math Hy3 leads
Dolly 2.0-12b: 27.3 (#251), Hy3: 40.1 (#93)
| Benchmark | Dolly 2.0-12b | Hy3 |
|---|---|---|
| LMArena Math | 871 | 1475 |
Knowledge Not comparable
Dolly 2.0-12b: —, Hy3: 40.8 (#114)
| Benchmark | Dolly 2.0-12b | Hy3 |
|---|---|---|
| LMArena Expert | — | 1460 |
| ARC (AI2) Challenge | 39.6% | — |
| BoolQ | 56.3% | — |
| MMLU | 26.2% | — |
| OpenBookQA | 39.2% | — |
Multilingual Hy3 leads
Dolly 2.0-12b: 17.4 (#296), Hy3: 53.5 (#65)
| Benchmark | Dolly 2.0-12b | Hy3 |
|---|---|---|
| LMArena Non-English | 836 | 1426 |
| LMArena Chinese | 836 | 1493 |
| LMArena French | — | 1461 |
| LMArena German | — | 1439 |
| LMArena Japanese | — | 1392 |
| LMArena Korean | — | 1395 |
| LMArena Russian | — | 1432 |
| LMArena Spanish | — | 1456 |
Instruction Following Hy3 leads
Dolly 2.0-12b: 38.7 (#304), Hy3: 75.1 (#70)
| Benchmark | Dolly 2.0-12b | Hy3 |
|---|---|---|
| LMArena Instruction Following | 814 | 1426 |
Long Context Not comparable
Dolly 2.0-12b: —, Hy3: 44.1 (#75)
| Benchmark | Dolly 2.0-12b | Hy3 |
|---|---|---|
| LMArena Longer Query | — | 1442 |
Writing & Preference Hy3 leads
Dolly 2.0-12b: 15.2 (#311), Hy3: 62.2 (#81)
| Benchmark | Dolly 2.0-12b | Hy3 |
|---|---|---|
| LMArena Text | 851 | 1439 |
| LMArena Creative Writing | 864 | 1402 |
| LMArena Multi-Turn | 740 | 1436 |
Frequently asked questions
Is Dolly 2.0-12b better than Hy3?
Hy3 is the stronger model overall, scoring 44.2 to 25.5 on the Noometry Index.
Is Dolly 2.0-12b or Hy3 better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 23.4 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and Hy3 share?
9 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Hy3 has 19.