Model comparison
Mercury 2.5 vs StarCoder 2 3B
Neither Mercury 2.5 nor StarCoder 2 3B has enough public benchmark results to be ranked yet; the rows below show what has been published.
Last verified . 0 shared benchmarks.
NVIDIASummary
- StarCoder 2 3B has downloadable open weights; the other is API-only.
Side by side
| Mercury 2.5 | StarCoder 2 3B | |
|---|---|---|
| Provider | Inception | NVIDIA |
| Noometry Index | 30.2 | 35.8 |
| Released | 2026-09-08 | 2024-02-22 |
| Weights | Proprietary | Open |
| Context window | 260K | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.04 | — |
| Output $ / M tokens | $0.15 | — |
| Results tracked | 2 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Mercury 2.5: —, StarCoder 2 3B: 32.9
| Benchmark | Mercury 2.5 | StarCoder 2 3B |
|---|---|---|
| BigCodeBench Complete | — | 21.4% |
| ALE-Bench | 301.65 | — |
| HumanEval+ | — | 27.4% |
Reasoning Not comparable
Mercury 2.5: —, StarCoder 2 3B: —
| Benchmark | Mercury 2.5 | StarCoder 2 3B |
|---|---|---|
| Epoch Capabilities Index | — | 88.01 |
| WinoGrande | — | 57.1% |
Math Not comparable
Mercury 2.5: 22.4, StarCoder 2 3B: —
| Benchmark | Mercury 2.5 | StarCoder 2 3B |
|---|---|---|
| ProofBench | 3% | — |
| GSM8K | — | 21.6% |
Knowledge Not comparable
Mercury 2.5: —, StarCoder 2 3B: —
| Benchmark | Mercury 2.5 | StarCoder 2 3B |
|---|---|---|
| ARC (AI2) Challenge | — | 34.2% |
| MMLU | — | 36.6% |
Frequently asked questions
Is Mercury 2.5 better than StarCoder 2 3B?
Neither Mercury 2.5 nor StarCoder 2 3B has enough public benchmark results to be ranked yet; the rows below show what has been published.
How many benchmarks do Mercury 2.5 and StarCoder 2 3B share?
0 benchmarks have published results for both models. Mercury 2.5 has 2 scored results on Noometry and StarCoder 2 3B has 7.