# GPT-5.2 Pro vs Mercury 2

> GPT-5.2 Pro is the stronger model overall, scoring 52.2 to 38.8 on the Noometry Index. Mercury 2 costs 154× less per token, which makes it the better buy when GPT-5.2 Pro's lead doesn't matter for your workload.

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

## Summary

- The widest gap is in reasoning, where GPT-5.2 Pro leads 51.8 to 23.0.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $21 / $168 for GPT-5.2 Pro.
- GPT-5.2 Pro accepts more context: 400K tokens versus 128K.

## Snapshot

| | GPT-5.2 Pro | Mercury 2 |
|---|---|---|
| Provider | OpenAI | Inception |
| Noometry Index | 52.2 | 38.8 |
| Rank | 34 | 167 |
| Context | 400K | 128K |
| Input $/M | $21 | $0.25 |
| Output $/M | $168 | $0.75 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5.2 Pro: —
- Mercury 2: 33.2 (#250)

| Benchmark | GPT-5.2 Pro | Mercury 2 |
|---|---|---|
| LMArena WebDev | — | 1170 |
| SciCode | — | 38.7% |
| WeirdML | — | 43.2% |
| LMArena Coding | — | 1391 |
| ALE-Bench | — | 785.58 |

## Reasoning

- GPT-5.2 Pro: 51.8 (#31)
- Mercury 2: 23.0 (#170)

| Benchmark | GPT-5.2 Pro | Mercury 2 |
|---|---|---|
| ARC-AGI-2 | 54.2% | — |
| SimpleBench | 57.4% | — |
| NYT Connections (extended) | 79.3% | — |
| ARC-AGI-1 | 90.5% | — |
| CritPt | — | 0.8% |
| LMArena Hard Prompts | — | 1362 |
| Epoch Capabilities Index | 155.41 | — |

## Math

- GPT-5.2 Pro: 64.8 (#23)
- Mercury 2: —

| Benchmark | GPT-5.2 Pro | Mercury 2 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 74% | — |
| FrontierMath Tier 4 | 46% | — |
| FrontierMath Tier 4 (v1) | 31.3% | — |

## Knowledge

- GPT-5.2 Pro: —
- Mercury 2: 35.6 (#170)

| Benchmark | GPT-5.2 Pro | Mercury 2 |
|---|---|---|
| Vectara Hallucination Rate | — | 12.3% |
| LMArena Expert | — | 1358 |

## Multilingual

- GPT-5.2 Pro: —
- Mercury 2: 46.8 (#153)

| Benchmark | GPT-5.2 Pro | Mercury 2 |
|---|---|---|
| LMArena Non-English | — | 1331 |
| LMArena Chinese | — | 1416 |
| LMArena Russian | — | 1303 |

## Instruction Following

- GPT-5.2 Pro: —
- Mercury 2: 70.4 (#161)

| Benchmark | GPT-5.2 Pro | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | — | 1328 |

## Long Context

- GPT-5.2 Pro: —
- Mercury 2: 40.4 (#149)

| Benchmark | GPT-5.2 Pro | Mercury 2 |
|---|---|---|
| LMArena Longer Query | — | 1329 |

## Writing & Preference

- GPT-5.2 Pro: —
- Mercury 2: 54.0 (#151)

| Benchmark | GPT-5.2 Pro | Mercury 2 |
|---|---|---|
| LMArena Text | — | 1355 |
| LMArena Creative Writing | — | 1289 |
| LMArena Multi-Turn | — | 1358 |

## FAQ

### Is GPT-5.2 Pro better than Mercury 2?

GPT-5.2 Pro is the stronger model overall, scoring 52.2 to 38.8 on the Noometry Index. Mercury 2 costs 154× less per token, which makes it the better buy when GPT-5.2 Pro's lead doesn't matter for your workload.

### Which is cheaper, GPT-5.2 Pro or Mercury 2?

Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; GPT-5.2 Pro lists at $21 and $168.

### Which has the bigger context window?

GPT-5.2 Pro does, with 400K tokens against 128K.

### How many benchmarks do GPT-5.2 Pro and Mercury 2 share?

0 benchmarks have published results for both models. GPT-5.2 Pro has 8 scored results on Noometry and Mercury 2 has 17.