Model comparison
Hy3 vs Tulu 3 (Tülu 3) 70B
Hy3 is the stronger model overall, scoring 44.2 to 33.0 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 Tulu 3 (Tülu 3) 70B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Hy3 leads 40.1 to 14.2.
Side by side
| Hy3 | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Tencent | Allen Institute for AI (Ai2) |
| Noometry Index | 44.2 | 33.0 |
| Released | 2026-07-06 | 2024-11-21 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.0825 | — |
| Output $ / M tokens | $0.33 | — |
| Results tracked | 19 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.8 (#63), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Hy3 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1464 | 1235 |
| LMArena WebDev | 1508 | — |
Reasoning Hy3 leads
Hy3: 26.1 (#136), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Hy3 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1220 |
| NYT Connections (extended) | 41.2% | — |
Math Hy3 leads
Hy3: 40.1 (#93), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Hy3 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Math | 1475 | 1242 |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| MATH Level 5 | — | 42.7% |
Knowledge Hy3 leads
Hy3: 40.8 (#114), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Hy3 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
| LMArena Expert | 1460 | — |
Multilingual Hy3 leads
Hy3: 53.5 (#65), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Hy3 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1426 | 1236 |
| LMArena Chinese | 1493 | 1249 |
| LMArena Russian | 1432 | 1246 |
| LMArena French | 1461 | — |
| LMArena German | 1439 | — |
| LMArena Japanese | 1392 | — |
| LMArena Korean | 1395 | — |
| LMArena Spanish | 1456 | — |
Instruction Following Hy3 leads
Hy3: 75.1 (#70), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Hy3 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1426 | 1233 |
Long Context Hy3 leads
Hy3: 44.1 (#75), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Hy3 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1442 | 1224 |
Writing & Preference Hy3 leads
Hy3: 62.2 (#81), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Hy3 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1439 | 1256 |
| LMArena Creative Writing | 1402 | 1231 |
| LMArena Multi-Turn | 1436 | 1252 |
Frequently asked questions
Is Hy3 better than Tulu 3 (Tülu 3) 70B?
Hy3 is the stronger model overall, scoring 44.2 to 33.0 on the Noometry Index.
Is Hy3 or Tulu 3 (Tülu 3) 70B better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 36.0 in the Noometry coding category.
How many benchmarks do Hy3 and Tulu 3 (Tülu 3) 70B share?
11 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.