# DeepSeek Coder 33B vs GPT-5.2 Pro

> GPT-5.2 Pro has enough public results to be ranked (#39); DeepSeek Coder 33B does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/deepseek-coder-33b-vs-gpt-5-2-pro
- Last updated: 2026-10-12
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both.
- DeepSeek Coder 33B has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek Coder 33B | GPT-5.2 Pro |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 38.9 | 52.3 |
| Rank | — | 39 |
| Context | — | 400K |
| Input $/M | — | $21 |
| Output $/M | — | $168 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek Coder 33B: 38.0 (#184)
- GPT-5.2 Pro: —

| Benchmark | DeepSeek Coder 33B | GPT-5.2 Pro |
|---|---|---|
| BigCodeBench Instruct | 42% | — |
| BigCodeBench Complete | 51.1% | — |
| HumanEval+ | 75% | — |
| MBPP+ | 70.1% | — |

## Reasoning

- DeepSeek Coder 33B: —
- GPT-5.2 Pro: 51.5 (#33)

| Benchmark | DeepSeek Coder 33B | GPT-5.2 Pro |
|---|---|---|
| Epoch Capabilities Index | 96.32 | 155.4 |
| ARC-AGI-2 | — | 54.2% |
| SimpleBench | — | 57.4% |
| NYT Connections (extended) | — | 79.3% |
| ARC-AGI-1 | — | 90.5% |
| WinoGrande | 62% | — |

## Math

- DeepSeek Coder 33B: —
- GPT-5.2 Pro: 65.3 (#29)

| Benchmark | DeepSeek Coder 33B | GPT-5.2 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 74% |
| FrontierMath Tier 4 | — | 46% |
| FrontierMath Tier 4 (v1) | — | 31.3% |
| GSM8K | 35.4% | — |

## Knowledge

- DeepSeek Coder 33B: —
- GPT-5.2 Pro: —

| Benchmark | DeepSeek Coder 33B | GPT-5.2 Pro |
|---|---|---|
| ARC (AI2) Challenge | 42.2% | — |
| MMLU | 39.4% | — |

## FAQ

### Is DeepSeek Coder 33B better than GPT-5.2 Pro?

GPT-5.2 Pro has enough public results to be ranked (#39); DeepSeek Coder 33B does not yet, so treat this comparison as directional.

### How many benchmarks do DeepSeek Coder 33B and GPT-5.2 Pro share?

1 benchmark has published results for both models. DeepSeek Coder 33B has 9 scored results on Noometry and GPT-5.2 Pro has 8.