Model comparison
Granite 3.1 2b Instruct vs Qwen1.5 4b Chat
Granite 3.1 2b Instruct is the stronger model overall, scoring 33.2 to 28.8 on the Noometry Index.
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 8 categories and Qwen1.5 4b Chat in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Granite 3.1 2b Instruct leads 34.1 to 23.8.
Side by side
| Granite 3.1 2b Instruct | Qwen1.5 4b Chat | |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 33.2 | 28.8 |
| Released | — | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 12 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 33.4 (#257), Qwen1.5 4b Chat: 29.1 (#308)
| Benchmark | Granite 3.1 2b Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Coding | 1149 | 999 |
Reasoning Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 22.0 (#209), Qwen1.5 4b Chat: 18.5 (#279)
| Benchmark | Granite 3.1 2b Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Hard Prompts | 1138 | 976 |
Math Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 33.1 (#206), Qwen1.5 4b Chat: 30.4 (#234)
| Benchmark | Granite 3.1 2b Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Math | 1159 | 1026 |
Knowledge Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 30.8 (#224), Qwen1.5 4b Chat: 26.7 (#255)
| Benchmark | Granite 3.1 2b Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Expert | 1131 | 980 |
Multilingual Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 29.1 (#269), Qwen1.5 4b Chat: 24.1 (#290)
| Benchmark | Granite 3.1 2b Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Non-English | 1068 | 979 |
| LMArena Chinese | 1139 | 1024 |
| LMArena Russian | 1063 | 952 |
| LMArena German | — | 902 |
Instruction Following Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 57.7 (#264), Qwen1.5 4b Chat: 49.0 (#300)
| Benchmark | Granite 3.1 2b Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Instruction Following | 1116 | 978 |
Long Context Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 35.0 (#244), Qwen1.5 4b Chat: 30.1 (#290)
| Benchmark | Granite 3.1 2b Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Longer Query | 1155 | 988 |
Writing & Preference Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 34.1 (#274), Qwen1.5 4b Chat: 23.8 (#309)
| Benchmark | Granite 3.1 2b Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Text | 1127 | 997 |
| LMArena Creative Writing | 1116 | 969 |
| LMArena Multi-Turn | 1099 | 977 |
Frequently asked questions
Is Granite 3.1 2b Instruct better than Qwen1.5 4b Chat?
Granite 3.1 2b Instruct is the stronger model overall, scoring 33.2 to 28.8 on the Noometry Index.
Is Granite 3.1 2b Instruct or Qwen1.5 4b Chat better for coding?
Granite 3.1 2b Instruct scores higher on coding benchmarks: 33.4 versus 29.1 in the Noometry coding category.
How many benchmarks do Granite 3.1 2b Instruct and Qwen1.5 4b Chat share?
12 benchmarks have published results for both models. Granite 3.1 2b Instruct has 12 scored results on Noometry and Qwen1.5 4b Chat has 13.