Model comparison
Granite 3.1 8b Instruct vs Hy3
Hy3 is the stronger model overall, scoring 44.2 to 32.4 on the Noometry Index.
Last verified . 12 shared benchmarks.
TencentSummary
- They share 12 benchmarks with published results for both. Granite 3.1 8b Instruct scores higher in 0 categories and Hy3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Hy3 leads 62.2 to 35.5.
Side by side
| Granite 3.1 8b Instruct | Hy3 | |
|---|---|---|
| Provider | IBM | Tencent |
| Noometry Index | 32.4 | 44.2 |
| Released | — | 2026-07-06 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.0825 |
| Output $ / M tokens | — | $0.33 |
| Results tracked | 13 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Granite 3.1 8b Instruct: 34.5 (#233), Hy3: 46.8 (#63)
| Benchmark | Granite 3.1 8b Instruct | Hy3 |
|---|---|---|
| LMArena Coding | 1186 | 1464 |
| LMArena WebDev | — | 1508 |
Agentic & Tool Use Not comparable
Granite 3.1 8b Instruct: 24.1 (#120), Hy3: —
| Benchmark | Granite 3.1 8b Instruct | Hy3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | — |
Reasoning Hy3 leads
Granite 3.1 8b Instruct: 22.1 (#207), Hy3: 26.1 (#136)
| Benchmark | Granite 3.1 8b Instruct | Hy3 |
|---|---|---|
| LMArena Hard Prompts | 1145 | 1447 |
| NYT Connections (extended) | — | 41.2% |
Math Hy3 leads
Granite 3.1 8b Instruct: 33.0 (#209), Hy3: 40.1 (#93)
| Benchmark | Granite 3.1 8b Instruct | Hy3 |
|---|---|---|
| LMArena Math | 1152 | 1475 |
Knowledge Hy3 leads
Granite 3.1 8b Instruct: 31.1 (#220), Hy3: 40.8 (#114)
| Benchmark | Granite 3.1 8b Instruct | Hy3 |
|---|---|---|
| LMArena Expert | 1142 | 1460 |
Multilingual Hy3 leads
Granite 3.1 8b Instruct: 30.9 (#260), Hy3: 53.5 (#65)
| Benchmark | Granite 3.1 8b Instruct | Hy3 |
|---|---|---|
| LMArena Non-English | 1099 | 1426 |
| LMArena Chinese | 1145 | 1493 |
| LMArena Russian | 1092 | 1432 |
| LMArena French | — | 1461 |
| LMArena German | — | 1439 |
| LMArena Japanese | — | 1392 |
| LMArena Korean | — | 1395 |
| LMArena Spanish | — | 1456 |
Instruction Following Hy3 leads
Granite 3.1 8b Instruct: 58.6 (#259), Hy3: 75.1 (#70)
| Benchmark | Granite 3.1 8b Instruct | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1131 | 1426 |
Long Context Hy3 leads
Granite 3.1 8b Instruct: 35.2 (#241), Hy3: 44.1 (#75)
| Benchmark | Granite 3.1 8b Instruct | Hy3 |
|---|---|---|
| LMArena Longer Query | 1162 | 1442 |
Writing & Preference Hy3 leads
Granite 3.1 8b Instruct: 35.5 (#266), Hy3: 62.2 (#81)
| Benchmark | Granite 3.1 8b Instruct | Hy3 |
|---|---|---|
| LMArena Text | 1150 | 1439 |
| LMArena Creative Writing | 1129 | 1402 |
| LMArena Multi-Turn | 1108 | 1436 |
Frequently asked questions
Is Granite 3.1 8b Instruct better than Hy3?
Hy3 is the stronger model overall, scoring 44.2 to 32.4 on the Noometry Index.
Is Granite 3.1 8b Instruct or Hy3 better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 34.5 in the Noometry coding category.
How many benchmarks do Granite 3.1 8b Instruct and Hy3 share?
12 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and Hy3 has 19.