Model comparison
Granite 3.0 2b Instruct vs Qwen1.5-14B
Qwen1.5-14B is the stronger model overall, scoring 32.1 to 30.2 on the Noometry Index.
Last verified . 12 shared benchmarks.
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Granite 3.0 2b Instruct scores higher in 0 categories and Qwen1.5-14B in 8 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in coding, where Qwen1.5-14B leads 32.5 to 27.8.
Side by side
| Granite 3.0 2b Instruct | Qwen1.5-14B | |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 30.2 | 32.1 |
| Released | — | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 13 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-14B leads
Granite 3.0 2b Instruct: 27.8 (#311), Qwen1.5-14B: 32.5 (#259)
| Benchmark | Granite 3.0 2b Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Coding | 1090 | 1138 |
| BigCodeBench Instruct | 20.5% | — |
Reasoning Too close to call
Granite 3.0 2b Instruct: 19.6 (#234), Qwen1.5-14B: 20.5 (#217)
| Benchmark | Granite 3.0 2b Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1113 |
Math Too close to call
Granite 3.0 2b Instruct: 29.7 (#215), Qwen1.5-14B: 29.9 (#214)
| Benchmark | Granite 3.0 2b Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Math | 1117 | 1125 |
Knowledge Too close to call
Granite 3.0 2b Instruct: 28.4 (#238), Qwen1.5-14B: 29.3 (#230)
| Benchmark | Granite 3.0 2b Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Expert | 1064 | 1094 |
| MMLU | — | 68.6% |
Multilingual Qwen1.5-14B leads
Granite 3.0 2b Instruct: 27.1 (#273), Qwen1.5-14B: 30.8 (#257)
| Benchmark | Granite 3.0 2b Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Non-English | 1033 | 1095 |
| LMArena Chinese | 1070 | 1147 |
| LMArena Russian | 1045 | 1046 |
| LMArena French | — | 1115 |
| LMArena German | — | 1043 |
| LMArena Japanese | — | 1019 |
| LMArena Spanish | — | 1085 |
Instruction Following Qwen1.5-14B leads
Granite 3.0 2b Instruct: 54.2 (#279), Qwen1.5-14B: 57.1 (#266)
| Benchmark | Granite 3.0 2b Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Instruction Following | 1056 | 1102 |
Long Context Qwen1.5-14B leads
Granite 3.0 2b Instruct: 32.5 (#263), Qwen1.5-14B: 33.7 (#252)
| Benchmark | Granite 3.0 2b Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Longer Query | 1071 | 1113 |
Writing & Preference Qwen1.5-14B leads
Granite 3.0 2b Instruct: 29.8 (#287), Qwen1.5-14B: 33.7 (#270)
| Benchmark | Granite 3.0 2b Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Text | 1080 | 1128 |
| LMArena Creative Writing | 1046 | 1091 |
| LMArena Multi-Turn | 1053 | 1110 |
Frequently asked questions
Is Granite 3.0 2b Instruct better than Qwen1.5-14B?
Qwen1.5-14B is the stronger model overall, scoring 32.1 to 30.2 on the Noometry Index.
Is Granite 3.0 2b Instruct or Qwen1.5-14B better for coding?
Qwen1.5-14B scores higher on coding benchmarks: 32.5 versus 27.8 in the Noometry coding category.
How many benchmarks do Granite 3.0 2b Instruct and Qwen1.5-14B share?
12 benchmarks have published results for both models. Granite 3.0 2b Instruct has 13 scored results on Noometry and Qwen1.5-14B has 17.