Model comparison
Qwen1.5-110B vs StarCoder 2 15B
Qwen1.5-110B has enough public results to be ranked (#231); StarCoder 2 15B does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
Alibaba (Qwen)
NVIDIASummary
- They share 1 benchmark with published results for both. Qwen1.5-110B scores higher in 0 categories and StarCoder 2 15B in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where StarCoder 2 15B leads 36.0 to 32.4.
- The biggest single-benchmark swing is BigCodeBench Complete: 44.4% for Qwen1.5-110B and 38.4% for StarCoder 2 15B.
Side by side
| Qwen1.5-110B | StarCoder 2 15B | |
|---|---|---|
| Provider | Alibaba (Qwen) | NVIDIA |
| Noometry Index | 33.6 | 37.5 |
| Released | 2024-04-25 | 2024-02-20 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 20 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding StarCoder 2 15B leads
Qwen1.5-110B: 32.4 (#260), StarCoder 2 15B: 36.0
| Benchmark | Qwen1.5-110B | StarCoder 2 15B |
|---|---|---|
| BigCodeBench Complete | 44.4% | 38.4% |
| BigCodeBench Instruct | 35% | — |
| LMArena Coding | 1184 | — |
| HumanEval+ | — | 37.8% |
Reasoning Not comparable
Qwen1.5-110B: 21.7 (#192), StarCoder 2 15B: —
| Benchmark | Qwen1.5-110B | StarCoder 2 15B |
|---|---|---|
| LMArena Hard Prompts | 1168 | — |
| Epoch Capabilities Index | — | 104.61 |
| ForecastBench | 57.7 | — |
| WinoGrande | — | 64.3% |
Math Not comparable
Qwen1.5-110B: 31.1 (#199), StarCoder 2 15B: —
| Benchmark | Qwen1.5-110B | StarCoder 2 15B |
|---|---|---|
| LMArena Math | 1185 | — |
| GSM8K | — | 57.7% |
Knowledge Not comparable
Qwen1.5-110B: 30.7 (#217), StarCoder 2 15B: —
| Benchmark | Qwen1.5-110B | StarCoder 2 15B |
|---|---|---|
| LMArena Expert | 1144 | — |
| ARC (AI2) Challenge | — | 47.2% |
| MMLU | — | 64.1% |
Multilingual Not comparable
Qwen1.5-110B: 33.8 (#245), StarCoder 2 15B: —
| Benchmark | Qwen1.5-110B | StarCoder 2 15B |
|---|---|---|
| LMArena Non-English | 1142 | — |
| LMArena Chinese | 1206 | — |
| LMArena French | 1150 | — |
| LMArena German | 1123 | — |
| LMArena Japanese | 1074 | — |
| LMArena Korean | 1044 | — |
| LMArena Russian | 1118 | — |
| LMArena Spanish | 1141 | — |
Instruction Following Not comparable
Qwen1.5-110B: 60.6 (#247), StarCoder 2 15B: —
| Benchmark | Qwen1.5-110B | StarCoder 2 15B |
|---|---|---|
| LMArena Instruction Following | 1158 | — |
Long Context Not comparable
Qwen1.5-110B: 35.0 (#237), StarCoder 2 15B: —
| Benchmark | Qwen1.5-110B | StarCoder 2 15B |
|---|---|---|
| LMArena Longer Query | 1157 | — |
Writing & Preference Not comparable
Qwen1.5-110B: 38.1 (#250), StarCoder 2 15B: —
| Benchmark | Qwen1.5-110B | StarCoder 2 15B |
|---|---|---|
| LMArena Text | 1175 | — |
| LMArena Creative Writing | 1148 | — |
| LMArena Multi-Turn | 1160 | — |
Frequently asked questions
Is Qwen1.5-110B better than StarCoder 2 15B?
Qwen1.5-110B has enough public results to be ranked (#231); StarCoder 2 15B does not yet, so treat this comparison as directional.
Is Qwen1.5-110B or StarCoder 2 15B better for coding?
StarCoder 2 15B scores higher on coding benchmarks: 36.0 versus 32.4 in the Noometry coding category.
How many benchmarks do Qwen1.5-110B and StarCoder 2 15B share?
1 benchmark has published results for both models. Qwen1.5-110B has 20 scored results on Noometry and StarCoder 2 15B has 7.