Model comparison
Phi 3 Mini 128k Instruct vs StarCoder 2 15B
Phi 3 Mini 128k Instruct has enough public results to be ranked (#305); StarCoder 2 15B does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
Microsoft
NVIDIASummary
- They share 1 benchmark with published results for both. Phi 3 Mini 128k Instruct scores higher in 0 categories and StarCoder 2 15B in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where StarCoder 2 15B leads 36.6 to 28.8.
Side by side
| Phi 3 Mini 128k Instruct | StarCoder 2 15B | |
|---|---|---|
| Provider | Microsoft | NVIDIA |
| Noometry Index | 29.7 | 38.1 |
| Released | 2024-04-23 | 2024-02-20 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding StarCoder 2 15B leads
Phi 3 Mini 128k Instruct: 28.8 (#312), StarCoder 2 15B: 36.6
| Benchmark | Phi 3 Mini 128k Instruct | StarCoder 2 15B |
|---|---|---|
| BigCodeBench Complete | 40.6% | 38.4% |
| BigCodeBench Instruct | 29.6% | — |
| LMArena Coding | 1039 | — |
| HumanEval+ | — | 37.8% |
Reasoning Not comparable
Phi 3 Mini 128k Instruct: 19.6 (#256), StarCoder 2 15B: —
| Benchmark | Phi 3 Mini 128k Instruct | StarCoder 2 15B |
|---|---|---|
| LMArena Hard Prompts | 1028 | — |
| Epoch Capabilities Index | — | 105 |
| WinoGrande | — | 64.3% |
Math Not comparable
Phi 3 Mini 128k Instruct: 31.6 (#222), StarCoder 2 15B: —
| Benchmark | Phi 3 Mini 128k Instruct | StarCoder 2 15B |
|---|---|---|
| LMArena Math | 1089 | — |
| GSM8K | — | 57.7% |
Knowledge Not comparable
Phi 3 Mini 128k Instruct: 26.8 (#254), StarCoder 2 15B: —
| Benchmark | Phi 3 Mini 128k Instruct | StarCoder 2 15B |
|---|---|---|
| LMArena Expert | 984 | — |
| ARC (AI2) Challenge | — | 47.2% |
| MMLU | — | 64.1% |
Multilingual Not comparable
Phi 3 Mini 128k Instruct: 25.2 (#285), StarCoder 2 15B: —
| Benchmark | Phi 3 Mini 128k Instruct | StarCoder 2 15B |
|---|---|---|
| LMArena Non-English | 1000 | — |
| LMArena Chinese | 1016 | — |
| LMArena French | 1039 | — |
| LMArena German | 1006 | — |
| LMArena Japanese | 899 | — |
| LMArena Korean | 856 | — |
| LMArena Russian | 1004 | — |
| LMArena Spanish | 1059 | — |
Instruction Following Not comparable
Phi 3 Mini 128k Instruct: 51.8 (#294), StarCoder 2 15B: —
| Benchmark | Phi 3 Mini 128k Instruct | StarCoder 2 15B |
|---|---|---|
| LMArena Instruction Following | 1023 | — |
Long Context Not comparable
Phi 3 Mini 128k Instruct: 30.4 (#289), StarCoder 2 15B: —
| Benchmark | Phi 3 Mini 128k Instruct | StarCoder 2 15B |
|---|---|---|
| LMArena Longer Query | 996 | — |
Writing & Preference Not comparable
Phi 3 Mini 128k Instruct: 27.1 (#301), StarCoder 2 15B: —
| Benchmark | Phi 3 Mini 128k Instruct | StarCoder 2 15B |
|---|---|---|
| LMArena Text | 1050 | — |
| LMArena Creative Writing | 1024 | — |
| LMArena Multi-Turn | 989 | — |
Frequently asked questions
Is Phi 3 Mini 128k Instruct better than StarCoder 2 15B?
Phi 3 Mini 128k Instruct has enough public results to be ranked (#305); StarCoder 2 15B does not yet, so treat this comparison as directional.
Is Phi 3 Mini 128k Instruct or StarCoder 2 15B better for coding?
StarCoder 2 15B scores higher on coding benchmarks: 36.6 versus 28.8 in the Noometry coding category.
How many benchmarks do Phi 3 Mini 128k Instruct and StarCoder 2 15B share?
1 benchmark has published results for both models. Phi 3 Mini 128k Instruct has 19 scored results on Noometry and StarCoder 2 15B has 7.