Model comparison
Granite 3.1 8b Instruct vs Hy4 preview
Hy4 preview is the stronger model overall, scoring 45.3 to 32.4 on the Noometry Index.
Last verified . 0 shared benchmarks.
TencentSummary
- The widest gap is in math, where Hy4 preview leads 55.7 to 33.0.
Side by side
| Granite 3.1 8b Instruct | Hy4 preview | |
|---|---|---|
| Provider | IBM | Tencent |
| Noometry Index | 32.4 | 45.3 |
| Released | — | 2026-08-28 |
| Weights | Open | Open |
| Context window | — | 1.05M |
| Max output | — | 64K |
| Input $ / M tokens | — | $0.83 |
| Output $ / M tokens | — | $2.50 |
| Results tracked | 13 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
Granite 3.1 8b Instruct: 34.5 (#233), Hy4 preview: 51.6 (#38)
| Benchmark | Granite 3.1 8b Instruct | Hy4 preview |
|---|---|---|
| LMArena WebDev | — | 1632 |
| LMArena Coding | 1186 | — |
Agentic & Tool Use Not comparable
Granite 3.1 8b Instruct: 24.1 (#120), Hy4 preview: —
| Benchmark | Granite 3.1 8b Instruct | Hy4 preview |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | — |
Reasoning Hy4 preview leads
Granite 3.1 8b Instruct: 22.1 (#207), Hy4 preview: 31.9 (#79)
| Benchmark | Granite 3.1 8b Instruct | Hy4 preview |
|---|---|---|
| NYT Connections (extended) | — | 68.2% |
| LMArena Hard Prompts | 1145 | — |
Math Hy4 preview leads
Granite 3.1 8b Instruct: 33.0 (#209), Hy4 preview: 55.7 (#42)
| Benchmark | Granite 3.1 8b Instruct | Hy4 preview |
|---|---|---|
| ProofBench | — | 75% |
| LMArena Math | 1152 | — |
Knowledge Not comparable
Granite 3.1 8b Instruct: 31.1 (#220), Hy4 preview: —
| Benchmark | Granite 3.1 8b Instruct | Hy4 preview |
|---|---|---|
| LMArena Expert | 1142 | — |
Multilingual Not comparable
Granite 3.1 8b Instruct: 30.9 (#260), Hy4 preview: —
| Benchmark | Granite 3.1 8b Instruct | Hy4 preview |
|---|---|---|
| LMArena Non-English | 1099 | — |
| LMArena Chinese | 1145 | — |
| LMArena Russian | 1092 | — |
Instruction Following Not comparable
Granite 3.1 8b Instruct: 58.6 (#259), Hy4 preview: —
| Benchmark | Granite 3.1 8b Instruct | Hy4 preview |
|---|---|---|
| LMArena Instruction Following | 1131 | — |
Long Context Not comparable
Granite 3.1 8b Instruct: 35.2 (#241), Hy4 preview: —
| Benchmark | Granite 3.1 8b Instruct | Hy4 preview |
|---|---|---|
| LMArena Longer Query | 1162 | — |
Writing & Preference Not comparable
Granite 3.1 8b Instruct: 35.5 (#266), Hy4 preview: —
| Benchmark | Granite 3.1 8b Instruct | Hy4 preview |
|---|---|---|
| LMArena Text | 1150 | — |
| LMArena Creative Writing | 1129 | — |
| LMArena Multi-Turn | 1108 | — |
Frequently asked questions
Is Granite 3.1 8b Instruct better than Hy4 preview?
Hy4 preview is the stronger model overall, scoring 45.3 to 32.4 on the Noometry Index.
Is Granite 3.1 8b Instruct or Hy4 preview better for coding?
Hy4 preview scores higher on coding benchmarks: 51.6 versus 34.5 in the Noometry coding category.
How many benchmarks do Granite 3.1 8b Instruct and Hy4 preview share?
0 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and Hy4 preview has 3.