# GPT-5.2 Pro vs Nova 2.0 Pro Preview

> GPT-5.2 Pro is the stronger model overall, scoring 52.2 to 32.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-2-pro-vs-nova-2-0-pro-preview
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where GPT-5.2 Pro leads 51.8 to 21.7.

## Snapshot

| | GPT-5.2 Pro | Nova 2.0 Pro Preview |
|---|---|---|
| Provider | OpenAI | Amazon |
| Noometry Index | 52.2 | 32.8 |
| Rank | 34 | 241 |
| Context | 400K | — |
| Input $/M | $21 | — |
| Output $/M | $168 | — |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5.2 Pro: —
- Nova 2.0 Pro Preview: 40.2 (#130)

| Benchmark | GPT-5.2 Pro | Nova 2.0 Pro Preview |
|---|---|---|
| SciCode | — | 42.7% |

## Agentic & Tool Use

- GPT-5.2 Pro: —
- Nova 2.0 Pro Preview: 21.9 (#127)

| Benchmark | GPT-5.2 Pro | Nova 2.0 Pro Preview |
|---|---|---|
| GDP.pdf | — | 2% |

## Reasoning

- GPT-5.2 Pro: 51.8 (#31)
- Nova 2.0 Pro Preview: 21.7 (#189)

| Benchmark | GPT-5.2 Pro | Nova 2.0 Pro Preview |
|---|---|---|
| ARC-AGI-2 | 54.2% | — |
| SimpleBench | 57.4% | — |
| NYT Connections (extended) | 79.3% | — |
| ARC-AGI-1 | 90.5% | — |
| CritPt | — | 0% |
| Epoch Capabilities Index | 155.41 | — |

## Math

- GPT-5.2 Pro: 64.8 (#23)
- Nova 2.0 Pro Preview: —

| Benchmark | GPT-5.2 Pro | Nova 2.0 Pro Preview |
|---|---|---|
| FrontierMath (Tiers 1-3) | 74% | — |
| FrontierMath Tier 4 | 46% | — |
| FrontierMath Tier 4 (v1) | 31.3% | — |

## FAQ

### Is GPT-5.2 Pro better than Nova 2.0 Pro Preview?

GPT-5.2 Pro is the stronger model overall, scoring 52.2 to 32.8 on the Noometry Index.

### How many benchmarks do GPT-5.2 Pro and Nova 2.0 Pro Preview share?

0 benchmarks have published results for both models. GPT-5.2 Pro has 8 scored results on Noometry and Nova 2.0 Pro Preview has 3.