# ERNIE 5.1 vs GPT-5

> GPT-5 is the stronger model overall, scoring 50.9 to 43.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ernie-5-1-vs-gpt-5
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. ERNIE 5.1 scores higher in 3 categories and GPT-5 in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where GPT-5 leads 69.5 to 44.7.

## Snapshot

| | ERNIE 5.1 | GPT-5 |
|---|---|---|
| Provider | Baidu | OpenAI |
| Noometry Index | 43.1 | 50.9 |
| Rank | 87 | 37 |
| Context | — | 400K |
| Input $/M | — | $1.25 |
| Output $/M | — | $10 |
| Weights | Proprietary | Proprietary |

## Coding

- ERNIE 5.1: 43.4 (#78)
- GPT-5: 50.7 (#39)

| Benchmark | ERNIE 5.1 | GPT-5 |
|---|---|---|
| LMArena Coding | 1488 | 1436 |
| SWE-bench Verified | — | 73.6% |
| SWE-bench Verified (bash only) | — | 65% |
| Aider Polyglot | — | 88% |
| LMArena WebDev | — | 1417 |
| SciCode | — | 42.9% |
| GSO | — | 6.9% |
| WeirdML | — | 60.7% |
| ALE-Bench | — | 1,162 |
| AlgoTune | — | 1.67 |

## Agentic & Tool Use

- ERNIE 5.1: —
- GPT-5: 33.0 (#53)

| Benchmark | ERNIE 5.1 | GPT-5 |
|---|---|---|
| LMArena Search | 1227 | 1133 |
| Terminal-Bench | — | 49.6% |
| GDPval | — | 34.8% |
| Remote Labor Index | — | 1.7% |
| DeepResearch Bench | — | 49.6% |
| BALROG | — | 32.8% |
| METR Time Horizons | — | 69.6% |

## Reasoning

- ERNIE 5.1: 20.9 (#209)
- GPT-5: 38.3 (#55)

| Benchmark | ERNIE 5.1 | GPT-5 |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1415 |
| ARC-AGI-2 | — | 9.9% |
| SimpleBench | — | 56.7% |
| Kagi LLM Benchmark | — | 72.7% |
| NYT Connections (extended) | 23.4% | — |
| ARC-AGI-1 | — | 65.7% |
| CritPt | — | 12.6% |
| Chess Puzzles | — | 37% |
| EnigmaEval | — | 10.5% |
| EBR-Bench | — | 12.7% |
| Mystery Game Puzzles | — | 23% |
| DTBench | — | 90.7% |
| LMCA | — | 40% |
| Epoch Capabilities Index | — | 150 |
| ForecastBench | — | 61.4 |

## Math

- ERNIE 5.1: 37.5 (#96)
- GPT-5: 54.6 (#36)

| Benchmark | ERNIE 5.1 | GPT-5 |
|---|---|---|
| LMArena Math | 1481 | 1406 |
| FrontierMath (Tiers 1-3) | — | 55.4% |
| FrontierMath Tier 4 | — | 22% |
| OTIS Mock AIME 2024-2025 | — | 91.4% |
| ProofBench | — | 18% |
| Omni-MATH | — | 64.7% |
| MATH Level 5 | — | 98.1% |
| FrontierMath (Feb 2025 set) | — | 32.4% |
| FrontierMath Tier 4 (v1) | — | 12.5% |

## Knowledge

- ERNIE 5.1: 41.2 (#103)
- GPT-5: 56.5 (#37)

| Benchmark | ERNIE 5.1 | GPT-5 |
|---|---|---|
| LMArena Expert | 1491 | 1420 |
| GPQA Diamond | — | 86.2% |
| Humanity's Last Exam | — | 25.3% |
| SimpleQA Verified | — | 50.1% |
| MMLU-Pro | — | 86.3% |
| Confabulations | — | 10.3% |
| Vectara Hallucination Rate | — | 14.7% |
| GPQA (HELM) | — | 79.2% |

## Multimodal

- ERNIE 5.1: —
- GPT-5: 46.1 (#12)

| Benchmark | ERNIE 5.1 | GPT-5 |
|---|---|---|
| LMArena Vision | — | 1232 |
| GeoBench | — | 81% |
| VPCT | — | 66% |

## Multilingual

- ERNIE 5.1: 55.7 (#28)
- GPT-5: 51.5 (#105)

| Benchmark | ERNIE 5.1 | GPT-5 |
|---|---|---|
| LMArena Non-English | 1455 | 1397 |
| LMArena Chinese | 1507 | 1423 |
| LMArena French | 1486 | 1409 |
| LMArena German | 1470 | 1415 |
| LMArena Japanese | 1422 | 1411 |
| LMArena Korean | 1428 | 1361 |
| LMArena Russian | 1459 | 1406 |
| LMArena Spanish | 1472 | 1398 |

## Instruction Following

- ERNIE 5.1: 76.9 (#35)
- GPT-5: 74.0 (#107)

| Benchmark | ERNIE 5.1 | GPT-5 |
|---|---|---|
| LMArena Instruction Following | 1460 | 1388 |
| IFEval | — | 87.5% |

## Long Context

- ERNIE 5.1: 44.7 (#56)
- GPT-5: 69.5 (#2)

| Benchmark | ERNIE 5.1 | GPT-5 |
|---|---|---|
| LMArena Longer Query | 1462 | 1399 |
| Fiction.LiveBench | — | 97.2% |

## Writing & Preference

- ERNIE 5.1: 65.3 (#50)
- GPT-5: 63.5 (#63)

| Benchmark | ERNIE 5.1 | GPT-5 |
|---|---|---|
| LMArena Text | 1468 | 1406 |
| LMArena Creative Writing | 1440 | 1365 |
| LMArena Multi-Turn | 1471 | 1426 |
| Short-Story Creative Writing | — | 86% |
| EQ-Bench Creative Writing | — | 1627 |
| WildBench | — | 85.7% |

## FAQ

### Is ERNIE 5.1 better than GPT-5?

GPT-5 is the stronger model overall, scoring 50.9 to 43.1 on the Noometry Index.

### Is ERNIE 5.1 or GPT-5 better for coding?

GPT-5 scores higher on coding benchmarks: 50.7 versus 43.4 in the Noometry coding category.

### How many benchmarks do ERNIE 5.1 and GPT-5 share?

18 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and GPT-5 has 69.