Model comparison
Qwen1.5-7B vs StarCoder 2 3B
Qwen1.5-7B has enough public results to be ranked (#270); StarCoder 2 3B 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. Qwen1.5-7B scores higher in 0 categories and StarCoder 2 3B in 1 category; one gap is clear of the uncertainty.
Side by side
| Qwen1.5-7B | StarCoder 2 3B | |
|---|---|---|
| Provider | Alibaba (Qwen) | NVIDIA |
| Noometry Index | 30.8 | 35.8 |
| Released | 2024-02-04 | 2024-02-22 |
| 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 3B leads
Qwen1.5-7B: 31.6 (#271), StarCoder 2 3B: 32.9
| Benchmark | Qwen1.5-7B | StarCoder 2 3B |
|---|---|---|
| LMArena Coding | 1107 | — |
| BigCodeBench Complete | — | 21.4% |
| HumanEval+ | — | 27.4% |
Reasoning Not comparable
Qwen1.5-7B: 19.5 (#237), StarCoder 2 3B: —
| Benchmark | Qwen1.5-7B | StarCoder 2 3B |
|---|---|---|
| LMArena Hard Prompts | 1066 | — |
| Epoch Capabilities Index | — | 88.01 |
| WinoGrande | — | 57.1% |
Math Not comparable
Qwen1.5-7B: 29.0 (#222), StarCoder 2 3B: —
| Benchmark | Qwen1.5-7B | StarCoder 2 3B |
|---|---|---|
| LMArena Math | 1080 | — |
| GSM8K | — | 21.6% |
Knowledge Not comparable
Qwen1.5-7B: 28.2 (#239), StarCoder 2 3B: —
| Benchmark | Qwen1.5-7B | StarCoder 2 3B |
|---|---|---|
| MMLU | 62.6% | 36.6% |
| LMArena Expert | 1055 | — |
| ARC (AI2) Challenge | — | 34.2% |
Multilingual Not comparable
Qwen1.5-7B: 28.6 (#266), StarCoder 2 3B: —
| Benchmark | Qwen1.5-7B | StarCoder 2 3B |
|---|---|---|
| LMArena Non-English | 1058 | — |
| LMArena Chinese | 1140 | — |
| LMArena Russian | 1006 | — |
Instruction Following Not comparable
Qwen1.5-7B: 54.4 (#276), StarCoder 2 3B: —
| Benchmark | Qwen1.5-7B | StarCoder 2 3B |
|---|---|---|
| LMArena Instruction Following | 1058 | — |
Long Context Not comparable
Qwen1.5-7B: 33.1 (#261), StarCoder 2 3B: —
| Benchmark | Qwen1.5-7B | StarCoder 2 3B |
|---|---|---|
| LMArena Longer Query | 1090 | — |
Writing & Preference Not comparable
Qwen1.5-7B: 29.8 (#288), StarCoder 2 3B: —
| Benchmark | Qwen1.5-7B | StarCoder 2 3B |
|---|---|---|
| LMArena Text | 1084 | — |
| LMArena Creative Writing | 1035 | — |
| LMArena Multi-Turn | 1061 | — |
Frequently asked questions
Is Qwen1.5-7B better than StarCoder 2 3B?
Qwen1.5-7B has enough public results to be ranked (#270); StarCoder 2 3B does not yet, so treat this comparison as directional.
Is Qwen1.5-7B or StarCoder 2 3B better for coding?
StarCoder 2 3B scores higher on coding benchmarks: 32.9 versus 31.6 in the Noometry coding category.
How many benchmarks do Qwen1.5-7B and StarCoder 2 3B share?
1 benchmark has published results for both models. Qwen1.5-7B has 13 scored results on Noometry and StarCoder 2 3B has 7.