Model comparison
Hy4 preview vs Tulu 3 (Tülu 3) 70B
Hy4 preview is the stronger model overall, scoring 45.3 to 33.0 on the Noometry Index.
Last verified . 0 shared benchmarks.
Tencent
Allen Institute for AI (Ai2)Summary
- The widest gap is in math, where Hy4 preview leads 55.7 to 14.2.
Side by side
| Hy4 preview | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Tencent | Allen Institute for AI (Ai2) |
| Noometry Index | 45.3 | 33.0 |
| Released | 2026-08-28 | 2024-11-21 |
| Weights | Open | Open |
| Context window | 1.05M | — |
| Max output | 64K | — |
| Input $ / M tokens | $0.75 | — |
| Output $ / M tokens | $2.25 | — |
| Results tracked | 3 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
Hy4 preview: 51.6 (#38), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Hy4 preview | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena WebDev | 1632 | — |
| LMArena Coding | — | 1235 |
Reasoning Hy4 preview leads
Hy4 preview: 31.9 (#79), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Hy4 preview | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| NYT Connections (extended) | 68.2% | — |
| LMArena Hard Prompts | — | 1220 |
Math Hy4 preview leads
Hy4 preview: 55.7 (#42), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Hy4 preview | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| ProofBench | 75% | — |
| LMArena Math | — | 1242 |
| MATH Level 5 | — | 42.7% |
Knowledge Not comparable
Hy4 preview: —, Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Hy4 preview | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
Multilingual Not comparable
Hy4 preview: —, Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Hy4 preview | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | — | 1236 |
| LMArena Chinese | — | 1249 |
| LMArena Russian | — | 1246 |
Instruction Following Not comparable
Hy4 preview: —, Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Hy4 preview | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | — | 1233 |
Long Context Not comparable
Hy4 preview: —, Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Hy4 preview | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | — | 1224 |
Writing & Preference Not comparable
Hy4 preview: —, Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Hy4 preview | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | — | 1256 |
| LMArena Creative Writing | — | 1231 |
| LMArena Multi-Turn | — | 1252 |
Frequently asked questions
Is Hy4 preview better than Tulu 3 (Tülu 3) 70B?
Hy4 preview is the stronger model overall, scoring 45.3 to 33.0 on the Noometry Index.
Is Hy4 preview or Tulu 3 (Tülu 3) 70B better for coding?
Hy4 preview scores higher on coding benchmarks: 51.6 versus 36.0 in the Noometry coding category.
How many benchmarks do Hy4 preview and Tulu 3 (Tülu 3) 70B share?
0 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.