# GPT-5.4 Pro vs Mercury

> GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 37.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-4-pro-vs-mercury
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where GPT-5.4 Pro leads 70.7 to 17.5.

## Snapshot

| | GPT-5.4 Pro | Mercury |
|---|---|---|
| Provider | OpenAI | Inception |
| Noometry Index | 58.9 | 37.6 |
| Rank | 18 | 199 |
| Context | 1.05M | — |
| Input $/M | $30 | — |
| Output $/M | $180 | — |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5.4 Pro: 43.2 (#90)
- Mercury: 38.7 (#170)

| Benchmark | GPT-5.4 Pro | Mercury |
|---|---|---|
| WeirdML | 57.4% | — |
| LMArena Coding | — | 1322 |

## Reasoning

- GPT-5.4 Pro: 70.7 (#13)
- Mercury: 17.5 (#293)

| Benchmark | GPT-5.4 Pro | Mercury |
|---|---|---|
| ARC-AGI-2 | 83.3% | — |
| SimpleBench | 74.1% | — |
| Kagi LLM Benchmark | — | 21.6% |
| ARC-AGI-1 | 94.5% | — |
| CritPt | 30% | — |
| Chess Puzzles | 58.6% | — |
| EnigmaEval | 23.8% | — |
| LMArena Hard Prompts | — | 1285 |
| Epoch Capabilities Index | 158.93 | — |

## Math

- GPT-5.4 Pro: 72.4 (#22)
- Mercury: —

| Benchmark | GPT-5.4 Pro | Mercury |
|---|---|---|
| FrontierMath (Tiers 1-3) | 82.5% | — |
| FrontierMath Tier 4 | 58.5% | — |
| FrontierMath (Feb 2025 set) | 50% | — |
| FrontierMath Tier 4 (v1) | 37.5% | — |

## Knowledge

- GPT-5.4 Pro: 68.3 (#7)
- Mercury: —

| Benchmark | GPT-5.4 Pro | Mercury |
|---|---|---|
| GPQA Diamond | 94.6% | — |
| Humanity's Last Exam | 44.3% | — |
| SimpleQA Verified | 46.3% | — |
| Vectara Hallucination Rate | 8.3% | — |

## Multilingual

- GPT-5.4 Pro: —
- Mercury: 41.6 (#206)

| Benchmark | GPT-5.4 Pro | Mercury |
|---|---|---|
| LMArena Non-English | — | 1260 |

## Instruction Following

- GPT-5.4 Pro: —
- Mercury: 65.2 (#224)

| Benchmark | GPT-5.4 Pro | Mercury |
|---|---|---|
| LMArena Instruction Following | — | 1239 |

## Long Context

- GPT-5.4 Pro: —
- Mercury: 38.4 (#198)

| Benchmark | GPT-5.4 Pro | Mercury |
|---|---|---|
| LMArena Longer Query | — | 1266 |

## Writing & Preference

- GPT-5.4 Pro: —
- Mercury: 46.2 (#221)

| Benchmark | GPT-5.4 Pro | Mercury |
|---|---|---|
| LMArena Text | — | 1282 |
| LMArena Creative Writing | — | 1191 |
| LMArena Multi-Turn | — | 1282 |

## FAQ

### Is GPT-5.4 Pro better than Mercury?

GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 37.6 on the Noometry Index.

### Is GPT-5.4 Pro or Mercury better for coding?

GPT-5.4 Pro scores higher on coding benchmarks: 43.2 versus 38.7 in the Noometry coding category.

### How many benchmarks do GPT-5.4 Pro and Mercury share?

0 benchmarks have published results for both models. GPT-5.4 Pro has 16 scored results on Noometry and Mercury has 9.