Model comparison
Granite 3.0 8b Instruct vs Qwen1.5-32B
Granite 3.0 8b Instruct is the stronger model overall, scoring 31.1 to 30.0 on the Noometry Index.
Last verified . 14 shared benchmarks.
Alibaba (Qwen)Summary
- They share 14 benchmarks with published results for both. Granite 3.0 8b Instruct scores higher in 1 category and Qwen1.5-32B in 7 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Granite 3.0 8b Instruct leads 29.1 to 13.5.
- The biggest single-benchmark swing is BigCodeBench Complete: 35.4% for Granite 3.0 8b Instruct and 42% for Qwen1.5-32B.
Side by side
| Granite 3.0 8b Instruct | Qwen1.5-32B | |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 31.1 | 30.0 |
| Released | — | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-32B leads
Granite 3.0 8b Instruct: 29.1 (#297), Qwen1.5-32B: 31.1 (#278)
| Benchmark | Granite 3.0 8b Instruct | Qwen1.5-32B |
|---|---|---|
| BigCodeBench Instruct | 29.3% | 32.3% |
| LMArena Coding | 1113 | 1155 |
| BigCodeBench Complete | 35.4% | 42% |
Reasoning Too close to call
Granite 3.0 8b Instruct: 20.0 (#227), Qwen1.5-32B: 20.9 (#210)
| Benchmark | Granite 3.0 8b Instruct | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1092 | 1131 |
Math Too close to call
Granite 3.0 8b Instruct: 30.3 (#211), Qwen1.5-32B: 30.5 (#207)
| Benchmark | Granite 3.0 8b Instruct | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1143 | 1155 |
Knowledge Granite 3.0 8b Instruct leads
Granite 3.0 8b Instruct: 29.1 (#233), Qwen1.5-32B: 13.5 (#291)
| Benchmark | Granite 3.0 8b Instruct | Qwen1.5-32B |
|---|---|---|
| LMArena Expert | 1087 | 1126 |
| GPQA Diamond | — | 30.7% |
| MMLU | — | 74.4% |
Multilingual Qwen1.5-32B leads
Granite 3.0 8b Instruct: 27.4 (#271), Qwen1.5-32B: 31.6 (#254)
| Benchmark | Granite 3.0 8b Instruct | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1037 | 1106 |
| LMArena Chinese | 1063 | 1176 |
| LMArena Russian | 1060 | 1073 |
| LMArena French | — | 1100 |
| LMArena German | — | 1058 |
| LMArena Japanese | — | 1027 |
| LMArena Korean | — | 1007 |
| LMArena Spanish | — | 1089 |
Instruction Following Qwen1.5-32B leads
Granite 3.0 8b Instruct: 56.2 (#271), Qwen1.5-32B: 58.0 (#260)
| Benchmark | Granite 3.0 8b Instruct | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1088 | 1116 |
Long Context Too close to call
Granite 3.0 8b Instruct: 34.0 (#247), Qwen1.5-32B: 34.7 (#241)
| Benchmark | Granite 3.0 8b Instruct | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1122 | 1146 |
Writing & Preference Qwen1.5-32B leads
Granite 3.0 8b Instruct: 31.2 (#280), Qwen1.5-32B: 34.4 (#266)
| Benchmark | Granite 3.0 8b Instruct | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1096 | 1137 |
| LMArena Creative Writing | 1071 | 1083 |
| LMArena Multi-Turn | 1063 | 1140 |
Frequently asked questions
Is Granite 3.0 8b Instruct better than Qwen1.5-32B?
Granite 3.0 8b Instruct is the stronger model overall, scoring 31.1 to 30.0 on the Noometry Index.
Is Granite 3.0 8b Instruct or Qwen1.5-32B better for coding?
Qwen1.5-32B scores higher on coding benchmarks: 31.1 versus 29.1 in the Noometry coding category.
How many benchmarks do Granite 3.0 8b Instruct and Qwen1.5-32B share?
14 benchmarks have published results for both models. Granite 3.0 8b Instruct has 14 scored results on Noometry and Qwen1.5-32B has 21.