# GPT-5 Pro vs Mercury

> GPT-5 Pro is the stronger model overall, scoring 46.4 to 37.6 on the Noometry Index.

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

## Summary

- They share 1 benchmark with published results for both. GPT-5 Pro scores higher in 2 categories and Mercury in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5 Pro leads 38.9 to 17.5.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 76.8% for GPT-5 Pro and 21.6% for Mercury.

## Snapshot

| | GPT-5 Pro | Mercury |
|---|---|---|
| Provider | OpenAI | Inception |
| Noometry Index | 46.4 | 37.6 |
| Rank | 64 | 199 |
| Context | 400K | — |
| Input $/M | $15 | — |
| Output $/M | $120 | — |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5 Pro: 44.0 (#80)
- Mercury: 38.7 (#170)

| Benchmark | GPT-5 Pro | Mercury |
|---|---|---|
| WeirdML | 60.4% | — |
| LMArena Coding | — | 1322 |
| AlgoTune | 1.31 | — |

## Reasoning

- GPT-5 Pro: 38.9 (#62)
- Mercury: 17.5 (#293)

| Benchmark | GPT-5 Pro | Mercury |
|---|---|---|
| Kagi LLM Benchmark | 76.8% | 21.6% |
| ARC-AGI-2 | 18.3% | — |
| SimpleBench | 61.6% | — |
| ARC-AGI-1 | 70.2% | — |
| EnigmaEval | 18.8% | — |
| LMArena Hard Prompts | — | 1285 |
| Epoch Capabilities Index | 150.28 | — |

## Math

- GPT-5 Pro: 48.5 (#63)
- Mercury: —

| Benchmark | GPT-5 Pro | Mercury |
|---|---|---|
| FrontierMath (Tiers 1-3) | 55.8% | — |
| FrontierMath Tier 4 | 19.5% | — |
| FrontierMath Tier 4 (v1) | 14.6% | — |

## Knowledge

- GPT-5 Pro: 56.7 (#42)
- Mercury: —

| Benchmark | GPT-5 Pro | Mercury |
|---|---|---|
| Humanity's Last Exam | 31.6% | — |

## Multilingual

- GPT-5 Pro: —
- Mercury: 41.6 (#206)

| Benchmark | GPT-5 Pro | Mercury |
|---|---|---|
| LMArena Non-English | — | 1260 |

## Instruction Following

- GPT-5 Pro: —
- Mercury: 65.2 (#224)

| Benchmark | GPT-5 Pro | Mercury |
|---|---|---|
| LMArena Instruction Following | — | 1239 |

## Long Context

- GPT-5 Pro: —
- Mercury: 38.4 (#198)

| Benchmark | GPT-5 Pro | Mercury |
|---|---|---|
| LMArena Longer Query | — | 1266 |

## Writing & Preference

- GPT-5 Pro: —
- Mercury: 46.2 (#221)

| Benchmark | GPT-5 Pro | Mercury |
|---|---|---|
| LMArena Text | — | 1282 |
| LMArena Creative Writing | — | 1191 |
| LMArena Multi-Turn | — | 1282 |

## FAQ

### Is GPT-5 Pro better than Mercury?

GPT-5 Pro is the stronger model overall, scoring 46.4 to 37.6 on the Noometry Index.

### Is GPT-5 Pro or Mercury better for coding?

GPT-5 Pro scores higher on coding benchmarks: 44.0 versus 38.7 in the Noometry coding category.

### How many benchmarks do GPT-5 Pro and Mercury share?

1 benchmark has published results for both models. GPT-5 Pro has 12 scored results on Noometry and Mercury has 9.