Model comparison
Phi 3 Medium 4k Instruct vs StarCoder 2 3B
Phi 3 Medium 4k Instruct has enough public results to be ranked (#246); StarCoder 2 3B does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Microsoft
NVIDIASide by side
| Phi 3 Medium 4k Instruct | StarCoder 2 3B | |
|---|---|---|
| Provider | Microsoft | NVIDIA |
| Noometry Index | 32.4 | 35.8 |
| Released | — | 2024-02-22 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Phi 3 Medium 4k Instruct: 32.3 (#263), StarCoder 2 3B: 32.9
| Benchmark | Phi 3 Medium 4k Instruct | StarCoder 2 3B |
|---|---|---|
| LMArena Coding | 1130 | — |
| BigCodeBench Complete | — | 21.4% |
| HumanEval+ | — | 27.4% |
Reasoning Not comparable
Phi 3 Medium 4k Instruct: 20.8 (#214), StarCoder 2 3B: —
| Benchmark | Phi 3 Medium 4k Instruct | StarCoder 2 3B |
|---|---|---|
| LMArena Hard Prompts | 1127 | — |
| Epoch Capabilities Index | — | 88.01 |
| WinoGrande | — | 57.1% |
Math Not comparable
Phi 3 Medium 4k Instruct: 30.9 (#202), StarCoder 2 3B: —
| Benchmark | Phi 3 Medium 4k Instruct | StarCoder 2 3B |
|---|---|---|
| LMArena Math | 1173 | — |
| GSM8K | — | 21.6% |
Knowledge Not comparable
Phi 3 Medium 4k Instruct: 29.6 (#226), StarCoder 2 3B: —
| Benchmark | Phi 3 Medium 4k Instruct | StarCoder 2 3B |
|---|---|---|
| LMArena Expert | 1108 | — |
| ARC (AI2) Challenge | — | 34.2% |
| MMLU | — | 36.6% |
Multilingual Not comparable
Phi 3 Medium 4k Instruct: 30.8 (#258), StarCoder 2 3B: —
| Benchmark | Phi 3 Medium 4k Instruct | StarCoder 2 3B |
|---|---|---|
| LMArena Non-English | 1094 | — |
| LMArena Chinese | 1108 | — |
| LMArena French | 1109 | — |
| LMArena German | 1101 | — |
| LMArena Japanese | 1042 | — |
| LMArena Korean | 954 | — |
| LMArena Russian | 1145 | — |
| LMArena Spanish | 1095 | — |
Instruction Following Not comparable
Phi 3 Medium 4k Instruct: 57.8 (#263), StarCoder 2 3B: —
| Benchmark | Phi 3 Medium 4k Instruct | StarCoder 2 3B |
|---|---|---|
| LMArena Instruction Following | 1114 | — |
Long Context Not comparable
Phi 3 Medium 4k Instruct: 33.9 (#250), StarCoder 2 3B: —
| Benchmark | Phi 3 Medium 4k Instruct | StarCoder 2 3B |
|---|---|---|
| LMArena Longer Query | 1120 | — |
Writing & Preference Not comparable
Phi 3 Medium 4k Instruct: 34.3 (#267), StarCoder 2 3B: —
| Benchmark | Phi 3 Medium 4k Instruct | StarCoder 2 3B |
|---|---|---|
| LMArena Text | 1138 | — |
| LMArena Creative Writing | 1106 | — |
| LMArena Multi-Turn | 1088 | — |
Frequently asked questions
Is Phi 3 Medium 4k Instruct better than StarCoder 2 3B?
Phi 3 Medium 4k Instruct has enough public results to be ranked (#246); StarCoder 2 3B does not yet, so treat this comparison as directional.
Is Phi 3 Medium 4k Instruct or StarCoder 2 3B better for coding?
They score almost the same on coding (32.3 vs 32.9); test both on your own repository before choosing.
How many benchmarks do Phi 3 Medium 4k Instruct and StarCoder 2 3B share?
0 benchmarks have published results for both models. Phi 3 Medium 4k Instruct has 17 scored results on Noometry and StarCoder 2 3B has 7.