Model comparison
Palm 2 vs StarCoder 2 3B
Palm 2 has enough public results to be ranked (#298); StarCoder 2 3B does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Google
NVIDIASummary
- The widest gap is in coding, where StarCoder 2 3B leads 33.5 to 29.0.
- StarCoder 2 3B has downloadable open weights; the other is API-only.
Side by side
| Palm 2 | StarCoder 2 3B | |
|---|---|---|
| Provider | NVIDIA | |
| Noometry Index | 30.0 | 36.3 |
| Released | — | 2024-02-22 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 10 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding StarCoder 2 3B leads
Palm 2: 29.0 (#311), StarCoder 2 3B: 33.5
| Benchmark | Palm 2 | StarCoder 2 3B |
|---|---|---|
| LMArena Coding | 994 | — |
| BigCodeBench Complete | — | 21.4% |
| HumanEval+ | — | 27.4% |
Reasoning Not comparable
Palm 2: 19.1 (#271), StarCoder 2 3B: —
| Benchmark | Palm 2 | StarCoder 2 3B |
|---|---|---|
| LMArena Hard Prompts | 1005 | — |
| Epoch Capabilities Index | — | 88.76 |
| WinoGrande | — | 57.1% |
Math Not comparable
Palm 2: 30.8 (#231), StarCoder 2 3B: —
| Benchmark | Palm 2 | StarCoder 2 3B |
|---|---|---|
| LMArena Math | 1049 | — |
| GSM8K | — | 21.6% |
Knowledge Not comparable
Palm 2: —, StarCoder 2 3B: —
| Benchmark | Palm 2 | StarCoder 2 3B |
|---|---|---|
| ARC (AI2) Challenge | — | 34.2% |
| MMLU | — | 36.6% |
Multilingual Not comparable
Palm 2: 20.9 (#295), StarCoder 2 3B: —
| Benchmark | Palm 2 | StarCoder 2 3B |
|---|---|---|
| LMArena Non-English | 916 | — |
| LMArena Chinese | 887 | — |
Instruction Following Not comparable
Palm 2: 51.0 (#296), StarCoder 2 3B: —
| Benchmark | Palm 2 | StarCoder 2 3B |
|---|---|---|
| LMArena Instruction Following | 1010 | — |
Long Context Not comparable
Palm 2: 30.8 (#285), StarCoder 2 3B: —
| Benchmark | Palm 2 | StarCoder 2 3B |
|---|---|---|
| LMArena Longer Query | 1010 | — |
Writing & Preference Not comparable
Palm 2: 25.6 (#304), StarCoder 2 3B: —
| Benchmark | Palm 2 | StarCoder 2 3B |
|---|---|---|
| LMArena Text | 1027 | — |
| LMArena Creative Writing | 991 | — |
| LMArena Multi-Turn | 994 | — |
Frequently asked questions
Is Palm 2 better than StarCoder 2 3B?
Palm 2 has enough public results to be ranked (#298); StarCoder 2 3B does not yet, so treat this comparison as directional.
Is Palm 2 or StarCoder 2 3B better for coding?
StarCoder 2 3B scores higher on coding benchmarks: 33.5 versus 29.0 in the Noometry coding category.
How many benchmarks do Palm 2 and StarCoder 2 3B share?
0 benchmarks have published results for both models. Palm 2 has 10 scored results on Noometry and StarCoder 2 3B has 7.