Model comparison
Granite 4.2 8B vs Qwen1.5-32B
Granite 4.2 8B is the stronger model overall, scoring 40.5 to 30.5 on the Noometry Index.
Last verified . 11 shared benchmarks.
Alibaba (Qwen)Summary
- They share 11 benchmarks with published results for both. Granite 4.2 8B scores higher in 7 categories and Qwen1.5-32B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Granite 4.2 8B leads 38.4 to 13.5.
Side by side
| Granite 4.2 8B | Qwen1.5-32B | |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 40.5 | 30.5 |
| Released | — | 2024-02-04 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 118K | — |
| Input $ / M tokens | $0.06 | — |
| Output $ / M tokens | $0.25 | — |
| Results tracked | 11 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 4.2 8B leads
Granite 4.2 8B: 40.5 (#137), Qwen1.5-32B: 31.7 (#282)
| Benchmark | Granite 4.2 8B | Qwen1.5-32B |
|---|---|---|
| LMArena Coding | 1380 | 1155 |
| BigCodeBench Instruct | — | 32.3% |
| BigCodeBench Complete | — | 42% |
Reasoning Granite 4.2 8B leads
Granite 4.2 8B: 26.6 (#131), Qwen1.5-32B: 21.8 (#212)
| Benchmark | Granite 4.2 8B | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1329 | 1130 |
Math Not comparable
Granite 4.2 8B: —, Qwen1.5-32B: 33.0 (#207)
| Benchmark | Granite 4.2 8B | Qwen1.5-32B |
|---|---|---|
| LMArena Math | — | 1155 |
Knowledge Granite 4.2 8B leads
Granite 4.2 8B: 38.4 (#145), Qwen1.5-32B: 13.5 (#296)
| Benchmark | Granite 4.2 8B | Qwen1.5-32B |
|---|---|---|
| LMArena Expert | 1384 | 1126 |
| GPQA Diamond | — | 30.7% |
| MMLU | — | 74.4% |
Multilingual Granite 4.2 8B leads
Granite 4.2 8B: 44.5 (#178), Qwen1.5-32B: 31.4 (#259)
| Benchmark | Granite 4.2 8B | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1302 | 1106 |
| LMArena Chinese | 1366 | 1177 |
| LMArena Russian | 1285 | 1073 |
| LMArena French | — | 1101 |
| LMArena German | — | 1058 |
| LMArena Japanese | — | 1027 |
| LMArena Korean | — | 1008 |
| LMArena Spanish | — | 1089 |
Instruction Following Granite 4.2 8B leads
Granite 4.2 8B: 68.7 (#184), Qwen1.5-32B: 57.7 (#265)
| Benchmark | Granite 4.2 8B | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1301 | 1116 |
Long Context Granite 4.2 8B leads
Granite 4.2 8B: 40.3 (#159), Qwen1.5-32B: 34.7 (#246)
| Benchmark | Granite 4.2 8B | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1324 | 1146 |
Writing & Preference Granite 4.2 8B leads
Granite 4.2 8B: 49.6 (#189), Qwen1.5-32B: 34.2 (#271)
| Benchmark | Granite 4.2 8B | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1320 | 1137 |
| LMArena Creative Writing | 1236 | 1083 |
| LMArena Multi-Turn | 1301 | 1140 |
Frequently asked questions
Is Granite 4.2 8B better than Qwen1.5-32B?
Granite 4.2 8B is the stronger model overall, scoring 40.5 to 30.5 on the Noometry Index.
Is Granite 4.2 8B or Qwen1.5-32B better for coding?
Granite 4.2 8B scores higher on coding benchmarks: 40.5 versus 31.7 in the Noometry coding category.
How many benchmarks do Granite 4.2 8B and Qwen1.5-32B share?
11 benchmarks have published results for both models. Granite 4.2 8B has 11 scored results on Noometry and Qwen1.5-32B has 21.