# ERNIE 5.1 vs GPT-5.4 Pro

> GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 43.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ernie-5-1-vs-gpt-5-4-pro
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where GPT-5.4 Pro leads 70.7 to 21.9.

## Snapshot

| | ERNIE 5.1 | GPT-5.4 Pro |
|---|---|---|
| Provider | Baidu | OpenAI |
| Noometry Index | 43.8 | 58.9 |
| Rank | 83 | 18 |
| Context | — | 1.05M |
| Input $/M | — | $30 |
| Output $/M | — | $180 |
| Weights | Proprietary | Proprietary |

## Coding

- ERNIE 5.1: 44.0 (#76)
- GPT-5.4 Pro: 43.2 (#90)

| Benchmark | ERNIE 5.1 | GPT-5.4 Pro |
|---|---|---|
| WeirdML | — | 57.4% |
| LMArena Coding | 1488 | — |

## Agentic & Tool Use

- ERNIE 5.1: —
- GPT-5.4 Pro: —

| Benchmark | ERNIE 5.1 | GPT-5.4 Pro |
|---|---|---|
| LMArena Search | 1227 | — |

## Reasoning

- ERNIE 5.1: 21.9 (#211)
- GPT-5.4 Pro: 70.7 (#13)

| Benchmark | ERNIE 5.1 | GPT-5.4 Pro |
|---|---|---|
| ARC-AGI-2 | — | 83.3% |
| SimpleBench | — | 74.1% |
| NYT Connections (extended) | 23.4% | — |
| ARC-AGI-1 | — | 94.5% |
| CritPt | — | 30% |
| Chess Puzzles | — | 58.6% |
| EnigmaEval | — | 23.8% |
| LMArena Hard Prompts | 1481 | — |
| Epoch Capabilities Index | — | 158.93 |

## Math

- ERNIE 5.1: 40.3 (#92)
- GPT-5.4 Pro: 72.4 (#22)

| Benchmark | ERNIE 5.1 | GPT-5.4 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 82.5% |
| FrontierMath Tier 4 | — | 58.5% |
| LMArena Math | 1481 | — |
| FrontierMath (Feb 2025 set) | — | 50% |
| FrontierMath Tier 4 (v1) | — | 37.5% |

## Knowledge

- ERNIE 5.1: 41.9 (#102)
- GPT-5.4 Pro: 68.3 (#7)

| Benchmark | ERNIE 5.1 | GPT-5.4 Pro |
|---|---|---|
| GPQA Diamond | — | 94.6% |
| Humanity's Last Exam | — | 44.3% |
| SimpleQA Verified | — | 46.3% |
| Vectara Hallucination Rate | — | 8.3% |
| LMArena Expert | 1492 | — |

## Multilingual

- ERNIE 5.1: 55.5 (#29)
- GPT-5.4 Pro: —

| Benchmark | ERNIE 5.1 | GPT-5.4 Pro |
|---|---|---|
| LMArena Non-English | 1454 | — |
| LMArena Chinese | 1508 | — |
| LMArena French | 1488 | — |
| LMArena German | 1470 | — |
| LMArena Japanese | 1422 | — |
| LMArena Korean | 1427 | — |
| LMArena Russian | 1459 | — |
| LMArena Spanish | 1473 | — |

## Instruction Following

- ERNIE 5.1: 76.7 (#37)
- GPT-5.4 Pro: —

| Benchmark | ERNIE 5.1 | GPT-5.4 Pro |
|---|---|---|
| LMArena Instruction Following | 1460 | — |

## Long Context

- ERNIE 5.1: 44.7 (#59)
- GPT-5.4 Pro: —

| Benchmark | ERNIE 5.1 | GPT-5.4 Pro |
|---|---|---|
| LMArena Longer Query | 1462 | — |

## Writing & Preference

- ERNIE 5.1: 65.1 (#52)
- GPT-5.4 Pro: —

| Benchmark | ERNIE 5.1 | GPT-5.4 Pro |
|---|---|---|
| LMArena Text | 1468 | — |
| LMArena Creative Writing | 1441 | — |
| LMArena Multi-Turn | 1471 | — |

## FAQ

### Is ERNIE 5.1 better than GPT-5.4 Pro?

GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 43.8 on the Noometry Index.

### Is ERNIE 5.1 or GPT-5.4 Pro better for coding?

They score almost the same on coding (44.0 vs 43.2); test both on your own repository before choosing.

### How many benchmarks do ERNIE 5.1 and GPT-5.4 Pro share?

0 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and GPT-5.4 Pro has 16.