# GPT-5 Pro vs StarCoder 2 3B

> GPT-5 Pro has enough public results to be ranked (#64); StarCoder 2 3B does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/gpt-5-pro-vs-starcoder-2-3b
- Last updated: 2026-10-12
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. GPT-5 Pro 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 GPT-5 Pro leads 44.0 to 33.5.
- StarCoder 2 3B has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5 Pro | StarCoder 2 3B |
|---|---|---|
| Provider | OpenAI | NVIDIA |
| Noometry Index | 46.4 | 36.3 |
| Rank | 64 | — |
| Context | 400K | — |
| Input $/M | $15 | — |
| Output $/M | $120 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-5 Pro: 44.0 (#80)
- StarCoder 2 3B: 33.5

| Benchmark | GPT-5 Pro | StarCoder 2 3B |
|---|---|---|
| WeirdML | 60.4% | — |
| BigCodeBench Complete | — | 21.4% |
| AlgoTune | 1.31 | — |
| HumanEval+ | — | 27.4% |

## Reasoning

- GPT-5 Pro: 38.9 (#62)
- StarCoder 2 3B: —

| Benchmark | GPT-5 Pro | StarCoder 2 3B |
|---|---|---|
| Epoch Capabilities Index | 150.28 | 88.76 |
| ARC-AGI-2 | 18.3% | — |
| SimpleBench | 61.6% | — |
| Kagi LLM Benchmark | 76.8% | — |
| ARC-AGI-1 | 70.2% | — |
| EnigmaEval | 18.8% | — |
| WinoGrande | — | 57.1% |

## Math

- GPT-5 Pro: 48.5 (#63)
- StarCoder 2 3B: —

| Benchmark | GPT-5 Pro | StarCoder 2 3B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 55.8% | — |
| FrontierMath Tier 4 | 19.5% | — |
| FrontierMath Tier 4 (v1) | 14.6% | — |
| GSM8K | — | 21.6% |

## Knowledge

- GPT-5 Pro: 56.7 (#42)
- StarCoder 2 3B: —

| Benchmark | GPT-5 Pro | StarCoder 2 3B |
|---|---|---|
| Humanity's Last Exam | 31.6% | — |
| ARC (AI2) Challenge | — | 34.2% |
| MMLU | — | 36.6% |

## FAQ

### Is GPT-5 Pro better than StarCoder 2 3B?

GPT-5 Pro has enough public results to be ranked (#64); StarCoder 2 3B does not yet, so treat this comparison as directional.

### Is GPT-5 Pro or StarCoder 2 3B better for coding?

GPT-5 Pro scores higher on coding benchmarks: 44.0 versus 33.5 in the Noometry coding category.

### How many benchmarks do GPT-5 Pro and StarCoder 2 3B share?

1 benchmark has published results for both models. GPT-5 Pro has 12 scored results on Noometry and StarCoder 2 3B has 7.