# GPT-5.5 Pro vs StarCoder 2 15B

> GPT-5.5 Pro has enough public results to be ranked (#8); StarCoder 2 15B does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/gpt-5-5-pro-vs-starcoder-2-15b
- Last updated: 2026-10-11
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both.
- StarCoder 2 15B has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.5 Pro | StarCoder 2 15B |
|---|---|---|
| Provider | OpenAI | NVIDIA |
| Noometry Index | 64.3 | 38.1 |
| Rank | 8 | — |
| Context | 1.05M | — |
| Input $/M | $30 | — |
| Output $/M | $180 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-5.5 Pro: —
- StarCoder 2 15B: 36.6

| Benchmark | GPT-5.5 Pro | StarCoder 2 15B |
|---|---|---|
| BigCodeBench Complete | — | 38.4% |
| HumanEval+ | — | 37.8% |

## Reasoning

- GPT-5.5 Pro: 73.3 (#10)
- StarCoder 2 15B: —

| Benchmark | GPT-5.5 Pro | StarCoder 2 15B |
|---|---|---|
| Epoch Capabilities Index | 162.07 | 105 |
| ARC-AGI-2 | 84.6% | — |
| SimpleBench | 76.9% | — |
| ARC-AGI-1 | 96.5% | — |
| CritPt | 30.6% | — |
| Chess Puzzles | 64% | — |
| DTBench | 96% | — |
| LMCA | 53.9% | — |
| WinoGrande | — | 64.3% |

## Math

- GPT-5.5 Pro: 84.0 (#10)
- StarCoder 2 15B: —

| Benchmark | GPT-5.5 Pro | StarCoder 2 15B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 87.7% | — |
| FrontierMath Tier 4 | 78% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| FrontierMath (Feb 2025 set) | 52.4% | — |
| FrontierMath Tier 4 (v1) | 39.6% | — |
| GSM8K | — | 57.7% |

## Knowledge

- GPT-5.5 Pro: 64.1 (#19)
- StarCoder 2 15B: —

| Benchmark | GPT-5.5 Pro | StarCoder 2 15B |
|---|---|---|
| GPQA Diamond | 93.9% | — |
| ARC (AI2) Challenge | — | 47.2% |
| MMLU | — | 64.1% |

## FAQ

### Is GPT-5.5 Pro better than StarCoder 2 15B?

GPT-5.5 Pro has enough public results to be ranked (#8); StarCoder 2 15B does not yet, so treat this comparison as directional.

### How many benchmarks do GPT-5.5 Pro and StarCoder 2 15B share?

1 benchmark has published results for both models. GPT-5.5 Pro has 14 scored results on Noometry and StarCoder 2 15B has 7.