Model comparison
Granite 4.1 8b vs Qwen1.5-14B
Granite 4.1 8b is the stronger model overall, scoring 37.4 to 32.7 on the Noometry Index.
Last verified . 12 shared benchmarks.
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Granite 4.1 8b scores higher in 7 categories and Qwen1.5-14B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Granite 4.1 8b leads 48.1 to 33.6.
Side by side
| Granite 4.1 8b | Qwen1.5-14B | |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 37.4 | 32.7 |
| Released | — | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 13 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-14B leads
Granite 4.1 8b: 30.1 (#297), Qwen1.5-14B: 33.1 (#263)
| Benchmark | Granite 4.1 8b | Qwen1.5-14B |
|---|---|---|
| LMArena Coding | 1312 | 1138 |
| LMArena WebDev | 1192 | — |
Reasoning Granite 4.1 8b leads
Granite 4.1 8b: 25.7 (#143), Qwen1.5-14B: 21.4 (#223)
| Benchmark | Granite 4.1 8b | Qwen1.5-14B |
|---|---|---|
| LMArena Hard Prompts | 1293 | 1113 |
Math Granite 4.1 8b leads
Granite 4.1 8b: 36.4 (#166), Qwen1.5-14B: 32.4 (#215)
| Benchmark | Granite 4.1 8b | Qwen1.5-14B |
|---|---|---|
| LMArena Math | 1312 | 1125 |
Knowledge Granite 4.1 8b leads
Granite 4.1 8b: 36.1 (#174), Qwen1.5-14B: 29.8 (#232)
| Benchmark | Granite 4.1 8b | Qwen1.5-14B |
|---|---|---|
| LMArena Expert | 1309 | 1094 |
| MMLU | — | 68.6% |
Multilingual Granite 4.1 8b leads
Granite 4.1 8b: 41.7 (#204), Qwen1.5-14B: 30.7 (#262)
| Benchmark | Granite 4.1 8b | Qwen1.5-14B |
|---|---|---|
| LMArena Non-English | 1261 | 1095 |
| LMArena Chinese | 1337 | 1147 |
| LMArena Russian | 1240 | 1046 |
| LMArena French | — | 1116 |
| LMArena German | — | 1043 |
| LMArena Japanese | — | 1019 |
| LMArena Spanish | — | 1085 |
Instruction Following Granite 4.1 8b leads
Granite 4.1 8b: 66.9 (#203), Qwen1.5-14B: 56.8 (#271)
| Benchmark | Granite 4.1 8b | Qwen1.5-14B |
|---|---|---|
| LMArena Instruction Following | 1269 | 1102 |
Long Context Granite 4.1 8b leads
Granite 4.1 8b: 38.7 (#193), Qwen1.5-14B: 33.7 (#257)
| Benchmark | Granite 4.1 8b | Qwen1.5-14B |
|---|---|---|
| LMArena Longer Query | 1275 | 1113 |
Writing & Preference Granite 4.1 8b leads
Granite 4.1 8b: 48.1 (#204), Qwen1.5-14B: 33.6 (#276)
| Benchmark | Granite 4.1 8b | Qwen1.5-14B |
|---|---|---|
| LMArena Text | 1290 | 1128 |
| LMArena Creative Writing | 1251 | 1091 |
| LMArena Multi-Turn | 1268 | 1110 |
Frequently asked questions
Is Granite 4.1 8b better than Qwen1.5-14B?
Granite 4.1 8b is the stronger model overall, scoring 37.4 to 32.7 on the Noometry Index.
Is Granite 4.1 8b or Qwen1.5-14B better for coding?
Qwen1.5-14B scores higher on coding benchmarks: 33.1 versus 30.1 in the Noometry coding category.
How many benchmarks do Granite 4.1 8b and Qwen1.5-14B share?
12 benchmarks have published results for both models. Granite 4.1 8b has 13 scored results on Noometry and Qwen1.5-14B has 17.