Model comparison
Granite 3.1 2b Instruct vs Qwen-14B
Granite 3.1 2b Instruct is the stronger model overall, scoring 33.2 to 31.4 on the Noometry Index.
Last verified . 10 shared benchmarks.
Alibaba (Qwen)Summary
- They share 10 benchmarks with published results for both. Granite 3.1 2b Instruct scores higher in 7 categories and Qwen-14B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Granite 3.1 2b Instruct leads 34.1 to 27.6.
Side by side
| Granite 3.1 2b Instruct | Qwen-14B | |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 33.2 | 31.4 |
| Released | — | 2023-09-24 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 12 | 18 |
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), Qwen-14B: 31.2 (#288)
| Benchmark | Granite 3.1 2b Instruct | Qwen-14B |
|---|---|---|
| LMArena Coding | 1149 | 1071 |
Reasoning Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 22.0 (#209), Qwen-14B: 19.6 (#257)
| Benchmark | Granite 3.1 2b Instruct | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1138 | 1027 |
| BIG-Bench Hard | — | 55% |
| Epoch Capabilities Index | — | 113.03 |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 33.1 (#206), Qwen-14B: 31.2 (#227)
| Benchmark | Granite 3.1 2b Instruct | Qwen-14B |
|---|---|---|
| LMArena Math | 1159 | 1068 |
| GSM8K | — | 61.3% |
Knowledge Not comparable
Granite 3.1 2b Instruct: 30.8 (#224), Qwen-14B: —
| Benchmark | Granite 3.1 2b Instruct | Qwen-14B |
|---|---|---|
| LMArena Expert | 1131 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multilingual Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 29.1 (#269), Qwen-14B: 27.5 (#275)
| Benchmark | Granite 3.1 2b Instruct | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1068 | 1041 |
| LMArena Chinese | 1139 | 1077 |
| LMArena Russian | 1063 | — |
Instruction Following Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 57.7 (#264), Qwen-14B: 52.4 (#289)
| Benchmark | Granite 3.1 2b Instruct | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1116 | 1031 |
Long Context Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 35.0 (#244), Qwen-14B: 31.3 (#280)
| Benchmark | Granite 3.1 2b Instruct | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1155 | 1028 |
Writing & Preference Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 34.1 (#274), Qwen-14B: 27.6 (#299)
| Benchmark | Granite 3.1 2b Instruct | Qwen-14B |
|---|---|---|
| LMArena Text | 1127 | 1051 |
| LMArena Creative Writing | 1116 | 1028 |
| LMArena Multi-Turn | 1099 | 1022 |
Frequently asked questions
Is Granite 3.1 2b Instruct better than Qwen-14B?
Granite 3.1 2b Instruct is the stronger model overall, scoring 33.2 to 31.4 on the Noometry Index.
Is Granite 3.1 2b Instruct or Qwen-14B better for coding?
Granite 3.1 2b Instruct scores higher on coding benchmarks: 33.4 versus 31.2 in the Noometry coding category.
How many benchmarks do Granite 3.1 2b Instruct and Qwen-14B share?
10 benchmarks have published results for both models. Granite 3.1 2b Instruct has 12 scored results on Noometry and Qwen-14B has 18.