Model comparison
Qwen2.5 7B Instruct vs StarCoder 2 15B
Qwen2.5 7B Instruct has enough public results to be ranked (#320); StarCoder 2 15B does not yet, so treat this comparison as directional.
Last verified . 3 shared benchmarks.
Alibaba (Qwen)
NVIDIASummary
- They share 3 benchmarks with published results for both. Qwen2.5 7B Instruct scores higher in 0 categories and StarCoder 2 15B in 1 category, but none of those gaps is larger than the uncertainty.
- The biggest single-benchmark swing is BigCodeBench Complete: 46.1% for Qwen2.5 7B Instruct and 38.4% for StarCoder 2 15B.
Side by side
| Qwen2.5 7B Instruct | StarCoder 2 15B | |
|---|---|---|
| Provider | Alibaba (Qwen) | NVIDIA |
| Noometry Index | 29.0 | 38.1 |
| Released | 2024-09 | 2024-02-20 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.17 | — |
| Output $ / M tokens | $0.70 | — |
| Results tracked | 15 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Qwen2.5 7B Instruct: 36.5 (#208), StarCoder 2 15B: 36.6
| Benchmark | Qwen2.5 7B Instruct | StarCoder 2 15B |
|---|---|---|
| BigCodeBench Complete | 46.1% | 38.4% |
| BigCodeBench Instruct | 37.6% | — |
| HumanEval+ | — | 37.8% |
Agentic & Tool Use Not comparable
Qwen2.5 7B Instruct: 23.8 (#124), StarCoder 2 15B: —
| Benchmark | Qwen2.5 7B Instruct | StarCoder 2 15B |
|---|---|---|
| BALROG | 7.8% | — |
Reasoning Not comparable
Qwen2.5 7B Instruct: 14.8 (#322), StarCoder 2 15B: —
| Benchmark | Qwen2.5 7B Instruct | StarCoder 2 15B |
|---|---|---|
| Epoch Capabilities Index | 118.51 | 105 |
| Chess Puzzles | 0% | — |
| DTBench | 47.7% | — |
| LMCA | 6.4% | — |
| WinoGrande | — | 64.3% |
Math Not comparable
Qwen2.5 7B Instruct: 12.6 (#306), StarCoder 2 15B: —
| Benchmark | Qwen2.5 7B Instruct | StarCoder 2 15B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| Omni-MATH | 29.4% | — |
| GSM8K | — | 57.7% |
Knowledge Not comparable
Qwen2.5 7B Instruct: 17.0 (#286), StarCoder 2 15B: —
| Benchmark | Qwen2.5 7B Instruct | StarCoder 2 15B |
|---|---|---|
| MMLU | 72.9% | 64.1% |
| GPQA Diamond | 35.5% | — |
| MMLU-Pro | 53.9% | — |
| GPQA (HELM) | 34.1% | — |
| ARC (AI2) Challenge | — | 47.2% |
Instruction Following Not comparable
Qwen2.5 7B Instruct: 63.2 (#231), StarCoder 2 15B: —
| Benchmark | Qwen2.5 7B Instruct | StarCoder 2 15B |
|---|---|---|
| IFEval | 74.1% | — |
Writing & Preference Not comparable
Qwen2.5 7B Instruct: 48.8 (#195), StarCoder 2 15B: —
| Benchmark | Qwen2.5 7B Instruct | StarCoder 2 15B |
|---|---|---|
| WildBench | 73.1% | — |
Frequently asked questions
Is Qwen2.5 7B Instruct better than StarCoder 2 15B?
Qwen2.5 7B Instruct has enough public results to be ranked (#320); StarCoder 2 15B does not yet, so treat this comparison as directional.
Is Qwen2.5 7B Instruct or StarCoder 2 15B better for coding?
They score almost the same on coding (36.5 vs 36.6); test both on your own repository before choosing.
How many benchmarks do Qwen2.5 7B Instruct and StarCoder 2 15B share?
3 benchmarks have published results for both models. Qwen2.5 7B Instruct has 15 scored results on Noometry and StarCoder 2 15B has 7.