Model comparison
Granite 3.1 2b Instruct vs Qwen2-72B
Granite 3.1 2b Instruct is the stronger model overall, scoring 33.2 to 30.0 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 3 categories and Qwen2-72B in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Granite 3.1 2b Instruct leads 30.8 to 21.2.
Side by side
| Granite 3.1 2b Instruct | Qwen2-72B | |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 33.2 | 30.0 |
| Released | — | 2024-06-07 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 12 | 26 |
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), Qwen2-72B: 29.1 (#310)
| Benchmark | Granite 3.1 2b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1149 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
Agentic & Tool Use Not comparable
Granite 3.1 2b Instruct: —, Qwen2-72B: 17.0 (#146)
| Benchmark | Granite 3.1 2b Instruct | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Granite 3.1 2b Instruct: 22.0 (#209), Qwen2-72B: 23.2 (#181)
| Benchmark | Granite 3.1 2b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1138 | 1191 |
| Epoch Capabilities Index | — | 125.28 |
Math Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 33.1 (#206), Qwen2-72B: 30.2 (#236)
| Benchmark | Granite 3.1 2b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Math | 1159 | 1235 |
| MATH Level 5 | — | 39.1% |
Knowledge Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 30.8 (#224), Qwen2-72B: 21.2 (#275)
| Benchmark | Granite 3.1 2b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1131 | 1171 |
| GPQA Diamond | — | 40.8% |
| MMLU | — | 82.4% |
Multilingual Qwen2-72B leads
Granite 3.1 2b Instruct: 29.1 (#269), Qwen2-72B: 35.9 (#244)
| Benchmark | Granite 3.1 2b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1068 | 1176 |
| LMArena Chinese | 1139 | 1240 |
| LMArena Russian | 1063 | 1169 |
| LMArena French | — | 1170 |
| LMArena German | — | 1151 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |
| LMArena Spanish | — | 1169 |
Instruction Following Qwen2-72B leads
Granite 3.1 2b Instruct: 57.7 (#264), Qwen2-72B: 61.7 (#241)
| Benchmark | Granite 3.1 2b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1116 | 1181 |
Long Context Qwen2-72B leads
Granite 3.1 2b Instruct: 35.0 (#244), Qwen2-72B: 36.1 (#235)
| Benchmark | Granite 3.1 2b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1155 | 1192 |
Writing & Preference Qwen2-72B leads
Granite 3.1 2b Instruct: 34.1 (#274), Qwen2-72B: 40.8 (#241)
| Benchmark | Granite 3.1 2b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Text | 1127 | 1203 |
| LMArena Creative Writing | 1116 | 1181 |
| LMArena Multi-Turn | 1099 | 1196 |
Frequently asked questions
Is Granite 3.1 2b Instruct better than Qwen2-72B?
Granite 3.1 2b Instruct is the stronger model overall, scoring 33.2 to 30.0 on the Noometry Index.
Is Granite 3.1 2b Instruct or Qwen2-72B 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 Qwen2-72B share?
12 benchmarks have published results for both models. Granite 3.1 2b Instruct has 12 scored results on Noometry and Qwen2-72B has 26.