Model comparison
Granite 3.1 2b Instruct vs Qwen1.5-110B
Granite 3.1 2b Instruct and Qwen1.5-110B score almost the same on the Noometry Index (32.6 vs 33.6), so choose on price, context window or the category you care about most.
Last verified . 12 shared benchmarks.
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Granite 3.1 2b Instruct scores higher in 1 category and Qwen1.5-110B in 7 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Qwen1.5-110B leads 33.8 to 29.2.
Side by side
| Granite 3.1 2b Instruct | Qwen1.5-110B | |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 32.6 | 33.6 |
| Released | — | 2024-04-25 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 12 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Granite 3.1 2b Instruct: 32.9 (#255), Qwen1.5-110B: 32.4 (#260)
| Benchmark | Granite 3.1 2b Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Coding | 1149 | 1184 |
| BigCodeBench Instruct | — | 35% |
| BigCodeBench Complete | — | 44.4% |
Reasoning Too close to call
Granite 3.1 2b Instruct: 21.0 (#206), Qwen1.5-110B: 21.7 (#192)
| Benchmark | Granite 3.1 2b Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Hard Prompts | 1138 | 1168 |
| ForecastBench | — | 57.7 |
Math Too close to call
Granite 3.1 2b Instruct: 30.6 (#206), Qwen1.5-110B: 31.1 (#199)
| Benchmark | Granite 3.1 2b Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Math | 1159 | 1185 |
Knowledge Too close to call
Granite 3.1 2b Instruct: 30.3 (#223), Qwen1.5-110B: 30.7 (#217)
| Benchmark | Granite 3.1 2b Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Expert | 1131 | 1144 |
Multilingual Qwen1.5-110B leads
Granite 3.1 2b Instruct: 29.2 (#264), Qwen1.5-110B: 33.8 (#245)
| Benchmark | Granite 3.1 2b Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Non-English | 1068 | 1142 |
| LMArena Chinese | 1138 | 1206 |
| LMArena Russian | 1063 | 1118 |
| LMArena French | — | 1150 |
| LMArena German | — | 1123 |
| LMArena Japanese | — | 1074 |
| LMArena Korean | — | 1044 |
| LMArena Spanish | — | 1141 |
Instruction Following Qwen1.5-110B leads
Granite 3.1 2b Instruct: 58.0 (#259), Qwen1.5-110B: 60.6 (#247)
| Benchmark | Granite 3.1 2b Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Instruction Following | 1116 | 1158 |
Long Context Too close to call
Granite 3.1 2b Instruct: 35.0 (#239), Qwen1.5-110B: 35.0 (#237)
| Benchmark | Granite 3.1 2b Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Longer Query | 1155 | 1157 |
Writing & Preference Qwen1.5-110B leads
Granite 3.1 2b Instruct: 34.3 (#269), Qwen1.5-110B: 38.1 (#250)
| Benchmark | Granite 3.1 2b Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Text | 1127 | 1175 |
| LMArena Creative Writing | 1116 | 1148 |
| LMArena Multi-Turn | 1099 | 1160 |
Frequently asked questions
Is Granite 3.1 2b Instruct better than Qwen1.5-110B?
Granite 3.1 2b Instruct and Qwen1.5-110B score almost the same on the Noometry Index (32.6 vs 33.6), so choose on price, context window or the category you care about most.
Is Granite 3.1 2b Instruct or Qwen1.5-110B better for coding?
They score almost the same on coding (32.9 vs 32.4); test both on your own repository before choosing.
How many benchmarks do Granite 3.1 2b Instruct and Qwen1.5-110B share?
12 benchmarks have published results for both models. Granite 3.1 2b Instruct has 12 scored results on Noometry and Qwen1.5-110B has 20.