Model comparison
Granite 3.1 8b Instruct vs Qwen1.5-72B
Granite 3.1 8b Instruct is the stronger model overall, scoring 32.4 to 30.8 on the Noometry Index.
Last verified . 12 shared benchmarks.
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Granite 3.1 8b Instruct scores higher in 3 categories and Qwen1.5-72B in 5 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Granite 3.1 8b Instruct leads 31.1 to 11.5.
Side by side
| Granite 3.1 8b Instruct | Qwen1.5-72B | |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 32.4 | 30.8 |
| Released | — | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 13 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 3.1 8b Instruct leads
Granite 3.1 8b Instruct: 34.5 (#233), Qwen1.5-72B: 31.9 (#277)
| Benchmark | Granite 3.1 8b Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Coding | 1186 | 1165 |
| BigCodeBench Instruct | — | 33.2% |
| BigCodeBench Complete | — | 40.3% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |
Agentic & Tool Use Not comparable
Granite 3.1 8b Instruct: 24.1 (#120), Qwen1.5-72B: —
| Benchmark | Granite 3.1 8b Instruct | Qwen1.5-72B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | — |
Reasoning Too close to call
Granite 3.1 8b Instruct: 22.1 (#207), Qwen1.5-72B: 22.2 (#203)
| Benchmark | Granite 3.1 8b Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1145 | 1148 |
Math Too close to call
Granite 3.1 8b Instruct: 33.0 (#209), Qwen1.5-72B: 33.2 (#205)
| Benchmark | Granite 3.1 8b Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1152 | 1164 |
Knowledge Granite 3.1 8b Instruct leads
Granite 3.1 8b Instruct: 31.1 (#220), Qwen1.5-72B: 11.5 (#300)
| Benchmark | Granite 3.1 8b Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Expert | 1142 | 1136 |
| GPQA Diamond | — | 28.8% |
Multilingual Qwen1.5-72B leads
Granite 3.1 8b Instruct: 30.9 (#260), Qwen1.5-72B: 33.2 (#253)
| Benchmark | Granite 3.1 8b Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1099 | 1135 |
| LMArena Chinese | 1145 | 1186 |
| LMArena Russian | 1092 | 1104 |
| LMArena French | — | 1159 |
| LMArena German | — | 1084 |
| LMArena Japanese | — | 1061 |
| LMArena Korean | — | 1050 |
| LMArena Spanish | — | 1110 |
Instruction Following Too close to call
Granite 3.1 8b Instruct: 58.6 (#259), Qwen1.5-72B: 59.3 (#256)
| Benchmark | Granite 3.1 8b Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1131 | 1141 |
Long Context Too close to call
Granite 3.1 8b Instruct: 35.2 (#241), Qwen1.5-72B: 35.1 (#243)
| Benchmark | Granite 3.1 8b Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1162 | 1157 |
Writing & Preference Qwen1.5-72B leads
Granite 3.1 8b Instruct: 35.5 (#266), Qwen1.5-72B: 37.3 (#258)
| Benchmark | Granite 3.1 8b Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1150 | 1166 |
| LMArena Creative Writing | 1129 | 1137 |
| LMArena Multi-Turn | 1108 | 1160 |
Frequently asked questions
Is Granite 3.1 8b Instruct better than Qwen1.5-72B?
Granite 3.1 8b Instruct is the stronger model overall, scoring 32.4 to 30.8 on the Noometry Index.
Is Granite 3.1 8b Instruct or Qwen1.5-72B better for coding?
Granite 3.1 8b Instruct scores higher on coding benchmarks: 34.5 versus 31.9 in the Noometry coding category.
How many benchmarks do Granite 3.1 8b Instruct and Qwen1.5-72B share?
12 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and Qwen1.5-72B has 22.