Model comparison
Phi-1.5 vs StarCoder 2 7B
Neither Phi-1.5 nor StarCoder 2 7B has enough public benchmark results to be ranked yet; the rows below show what has been published.
Last verified . 4 shared benchmarks.
Microsoft
NVIDIASummary
- They share 4 benchmarks with published results for both.
Side by side
| Phi-1.5 | StarCoder 2 7B | |
|---|---|---|
| Provider | Microsoft | NVIDIA |
| Noometry Index | — | 37.0 |
| Released | 2023-09-11 | 2024-02-20 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Phi-1.5: —, StarCoder 2 7B: 34.8
| Benchmark | Phi-1.5 | StarCoder 2 7B |
|---|---|---|
| BigCodeBench Complete | — | 27.7% |
| HumanEval+ | — | 29.9% |
Reasoning Not comparable
Phi-1.5: —, StarCoder 2 7B: —
| Benchmark | Phi-1.5 | StarCoder 2 7B |
|---|---|---|
| Epoch Capabilities Index | 91.53 | 93.56 |
| WinoGrande | 73.4% | 57.1% |
| HellaSwag | 47.6% | — |
Math Not comparable
Phi-1.5: —, StarCoder 2 7B: —
| Benchmark | Phi-1.5 | StarCoder 2 7B |
|---|---|---|
| GSM8K | — | 32.7% |
Knowledge Not comparable
Phi-1.5: —, StarCoder 2 7B: —
| Benchmark | Phi-1.5 | StarCoder 2 7B |
|---|---|---|
| ARC (AI2) Challenge | 44.4% | 38.7% |
| MMLU | 37.6% | 38.8% |
| BoolQ | 75.8% | — |
| OpenBookQA | 37.2% | — |
Frequently asked questions
Is Phi-1.5 better than StarCoder 2 7B?
Neither Phi-1.5 nor StarCoder 2 7B has enough public benchmark results to be ranked yet; the rows below show what has been published.
How many benchmarks do Phi-1.5 and StarCoder 2 7B share?
4 benchmarks have published results for both models. Phi-1.5 has 7 scored results on Noometry and StarCoder 2 7B has 7.