Model comparison
Qwen1.5 4b Chat vs StarCoder 2 15B
Qwen1.5 4b Chat has enough public results to be ranked (#319); StarCoder 2 15B does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)
NVIDIASummary
- The widest gap is in coding, where StarCoder 2 15B leads 36.0 to 28.6.
Side by side
| Qwen1.5 4b Chat | StarCoder 2 15B | |
|---|---|---|
| Provider | Alibaba (Qwen) | NVIDIA |
| Noometry Index | 28.3 | 37.5 |
| Released | — | 2024-02-20 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 13 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding StarCoder 2 15B leads
Qwen1.5 4b Chat: 28.6 (#305), StarCoder 2 15B: 36.0
| Benchmark | Qwen1.5 4b Chat | StarCoder 2 15B |
|---|---|---|
| LMArena Coding | 999 | — |
| BigCodeBench Complete | — | 38.4% |
| HumanEval+ | — | 37.8% |
Reasoning Not comparable
Qwen1.5 4b Chat: 17.7 (#277), StarCoder 2 15B: —
| Benchmark | Qwen1.5 4b Chat | StarCoder 2 15B |
|---|---|---|
| LMArena Hard Prompts | 976 | — |
| Epoch Capabilities Index | — | 104.61 |
| WinoGrande | — | 64.3% |
Math Not comparable
Qwen1.5 4b Chat: 27.9 (#233), StarCoder 2 15B: —
| Benchmark | Qwen1.5 4b Chat | StarCoder 2 15B |
|---|---|---|
| LMArena Math | 1026 | — |
| GSM8K | — | 57.7% |
Knowledge Not comparable
Qwen1.5 4b Chat: 26.2 (#252), StarCoder 2 15B: —
| Benchmark | Qwen1.5 4b Chat | StarCoder 2 15B |
|---|---|---|
| LMArena Expert | 980 | — |
| ARC (AI2) Challenge | — | 47.2% |
| MMLU | — | 64.1% |
Multilingual Not comparable
Qwen1.5 4b Chat: 24.2 (#285), StarCoder 2 15B: —
| Benchmark | Qwen1.5 4b Chat | StarCoder 2 15B |
|---|---|---|
| LMArena Non-English | 979 | — |
| LMArena Chinese | 1024 | — |
| LMArena German | 902 | — |
| LMArena Russian | 952 | — |
Instruction Following Not comparable
Qwen1.5 4b Chat: 49.3 (#295), StarCoder 2 15B: —
| Benchmark | Qwen1.5 4b Chat | StarCoder 2 15B |
|---|---|---|
| LMArena Instruction Following | 979 | — |
Long Context Not comparable
Qwen1.5 4b Chat: 30.1 (#285), StarCoder 2 15B: —
| Benchmark | Qwen1.5 4b Chat | StarCoder 2 15B |
|---|---|---|
| LMArena Longer Query | 988 | — |
Writing & Preference Not comparable
Qwen1.5 4b Chat: 23.9 (#304), StarCoder 2 15B: —
| Benchmark | Qwen1.5 4b Chat | StarCoder 2 15B |
|---|---|---|
| LMArena Text | 997 | — |
| LMArena Creative Writing | 969 | — |
| LMArena Multi-Turn | 977 | — |
Frequently asked questions
Is Qwen1.5 4b Chat better than StarCoder 2 15B?
Qwen1.5 4b Chat has enough public results to be ranked (#319); StarCoder 2 15B does not yet, so treat this comparison as directional.
Is Qwen1.5 4b Chat or StarCoder 2 15B better for coding?
StarCoder 2 15B scores higher on coding benchmarks: 36.0 versus 28.6 in the Noometry coding category.
How many benchmarks do Qwen1.5 4b Chat and StarCoder 2 15B share?
0 benchmarks have published results for both models. Qwen1.5 4b Chat has 13 scored results on Noometry and StarCoder 2 15B has 7.