Model comparison
Magistral Small vs StarCoder 2 3B
Magistral Small has enough public results to be ranked (#296); StarCoder 2 3B does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
Mistral AI
NVIDIASummary
- They share 1 benchmark with published results for both. Magistral Small scores higher in 1 category and StarCoder 2 3B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where Magistral Small leads 38.4 to 33.5.
Side by side
| Magistral Small | StarCoder 2 3B | |
|---|---|---|
| Provider | Mistral AI | NVIDIA |
| Noometry Index | 30.2 | 36.3 |
| Released | 2025-06-10 | 2024-02-22 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 40K | — |
| Input $ / M tokens | $0.50 | — |
| Output $ / M tokens | $1.50 | — |
| Results tracked | 10 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Small leads
Magistral Small: 38.4 (#176), StarCoder 2 3B: 33.5
| Benchmark | Magistral Small | StarCoder 2 3B |
|---|---|---|
| SciCode | 35.2% | — |
| BigCodeBench Complete | — | 21.4% |
| HumanEval+ | — | 27.4% |
Reasoning Not comparable
Magistral Small: 6.8 (#350), StarCoder 2 3B: —
| Benchmark | Magistral Small | StarCoder 2 3B |
|---|---|---|
| Epoch Capabilities Index | 133.19 | 88.76 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 6.3% | — |
| ARC-AGI-1 | 5% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | 3% | — |
| DTBench | 61.3% | — |
| WinoGrande | — | 57.1% |
Math Not comparable
Magistral Small: 26.2 (#261), StarCoder 2 3B: —
| Benchmark | Magistral Small | StarCoder 2 3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 30% | — |
| GSM8K | — | 21.6% |
Knowledge Not comparable
Magistral Small: 30.9 (#223), StarCoder 2 3B: —
| Benchmark | Magistral Small | StarCoder 2 3B |
|---|---|---|
| GPQA Diamond | 56.1% | — |
| ARC (AI2) Challenge | — | 34.2% |
| MMLU | — | 36.6% |
Frequently asked questions
Is Magistral Small better than StarCoder 2 3B?
Magistral Small has enough public results to be ranked (#296); StarCoder 2 3B does not yet, so treat this comparison as directional.
Is Magistral Small or StarCoder 2 3B better for coding?
Magistral Small scores higher on coding benchmarks: 38.4 versus 33.5 in the Noometry coding category.
How many benchmarks do Magistral Small and StarCoder 2 3B share?
1 benchmark has published results for both models. Magistral Small has 10 scored results on Noometry and StarCoder 2 3B has 7.