Model comparison
phi-3-medium 14B vs StarCoder 2 7B
phi-3-medium 14B has enough public results to be ranked (#306); StarCoder 2 7B does not yet, so treat this comparison as directional.
Last verified . 5 shared benchmarks.
Microsoft
NVIDIASummary
- They share 5 benchmarks with published results for both. phi-3-medium 14B scores higher in 1 category and StarCoder 2 7B in 0 categories; one gap is clear of the uncertainty.
- The biggest single-benchmark swing is BigCodeBench Complete: 48.7% for phi-3-medium 14B and 27.7% for StarCoder 2 7B.
Side by side
| phi-3-medium 14B | StarCoder 2 7B | |
|---|---|---|
| Provider | Microsoft | NVIDIA |
| Noometry Index | 29.7 | 37.0 |
| Released | 2024-04-23 | 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 phi-3-medium 14B leads
phi-3-medium 14B: 36.8 (#201), StarCoder 2 7B: 34.8
| Benchmark | phi-3-medium 14B | StarCoder 2 7B |
|---|---|---|
| BigCodeBench Complete | 48.7% | 27.7% |
| BigCodeBench Instruct | 37.6% | — |
| HumanEval+ | — | 29.9% |
Reasoning Not comparable
phi-3-medium 14B: —, StarCoder 2 7B: —
| Benchmark | phi-3-medium 14B | StarCoder 2 7B |
|---|---|---|
| Epoch Capabilities Index | 121.23 | 93.56 |
| WinoGrande | 81.5% | 57.1% |
| Adversarial NLI | 55.8% | — |
| BIG-Bench Hard | 81.4% | — |
| HellaSwag | 82.4% | — |
Math Not comparable
phi-3-medium 14B: 27.3 (#250), StarCoder 2 7B: —
| Benchmark | phi-3-medium 14B | StarCoder 2 7B |
|---|---|---|
| MATH Level 5 | 17.6% | — |
| GSM8K | — | 32.7% |
Knowledge Not comparable
phi-3-medium 14B: 9.1 (#306), StarCoder 2 7B: —
| Benchmark | phi-3-medium 14B | StarCoder 2 7B |
|---|---|---|
| ARC (AI2) Challenge | 91.6% | 38.7% |
| MMLU | 78% | 38.8% |
| GPQA Diamond | 27.6% | — |
| OpenBookQA | 87.4% | — |
| TriviaQA | 73.9% | — |
Frequently asked questions
Is phi-3-medium 14B better than StarCoder 2 7B?
phi-3-medium 14B has enough public results to be ranked (#306); StarCoder 2 7B does not yet, so treat this comparison as directional.
Is phi-3-medium 14B or StarCoder 2 7B better for coding?
phi-3-medium 14B scores higher on coding benchmarks: 36.8 versus 34.8 in the Noometry coding category.
How many benchmarks do phi-3-medium 14B and StarCoder 2 7B share?
5 benchmarks have published results for both models. phi-3-medium 14B has 13 scored results on Noometry and StarCoder 2 7B has 7.