# ERNIE 5.0 0110 vs GPT-4.5

> ERNIE 5.0 0110 is the stronger model overall, scoring 41.2 to 36.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ernie-5-0-vs-gpt-4-5
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. ERNIE 5.0 0110 scores higher in 9 categories and GPT-4.5 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where ERNIE 5.0 0110 leads 39.2 to 32.4.

## Snapshot

| | ERNIE 5.0 0110 | GPT-4.5 |
|---|---|---|
| Provider | Baidu | OpenAI |
| Noometry Index | 41.2 | 36.9 |
| Rank | 129 | 200 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Proprietary |

## Coding

- ERNIE 5.0 0110: 42.3 (#94)
- GPT-4.5: 41.8 (#102)

| Benchmark | ERNIE 5.0 0110 | GPT-4.5 |
|---|---|---|
| LMArena Coding | 1455 | 1397 |
| Aider Polyglot | — | 44.9% |
| WeirdML | — | 39.4% |
| LiveBench Coding | — | 75.2% |

## Agentic & Tool Use

- ERNIE 5.0 0110: —
- GPT-4.5: 27.6 (#92)

| Benchmark | ERNIE 5.0 0110 | GPT-4.5 |
|---|---|---|
| Cybench | — | 17.5% |

## Reasoning

- ERNIE 5.0 0110: 16.3 (#296)
- GPT-4.5: 14.1 (#320)

| Benchmark | ERNIE 5.0 0110 | GPT-4.5 |
|---|---|---|
| LMArena Hard Prompts | 1446 | 1404 |
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 34.5% |
| NYT Connections (extended) | 10.3% | — |
| ARC-AGI-1 | — | 10.3% |
| EnigmaEval | — | 3.2% |
| Thematic Generalization | 41.7% | — |
| LiveBench Reasoning | — | 71.1% |
| LiveBench Data Analysis | — | 64.3% |
| Epoch Capabilities Index | — | 136.74 |
| ForecastBench | — | 61.7 |
| LiveBench | — | 69% |

## Math

- ERNIE 5.0 0110: 36.5 (#111)
- GPT-4.5: 31.0 (#200)

| Benchmark | ERNIE 5.0 0110 | GPT-4.5 |
|---|---|---|
| LMArena Math | 1437 | 1412 |
| OTIS Mock AIME 2024-2025 | — | 37.8% |
| LiveBench Math | — | 69.3% |
| MATH Level 5 | — | 78.6% |

## Knowledge

- ERNIE 5.0 0110: 39.2 (#125)
- GPT-4.5: 32.4 (#205)

| Benchmark | ERNIE 5.0 0110 | GPT-4.5 |
|---|---|---|
| LMArena Expert | 1427 | 1394 |
| GPQA Diamond | — | 68.7% |
| Humanity's Last Exam | — | 5.4% |
| Confabulations | — | 13.6% |

## Multimodal

- ERNIE 5.0 0110: 39.1 (#49)
- GPT-4.5: 37.0 (#68)

| Benchmark | ERNIE 5.0 0110 | GPT-4.5 |
|---|---|---|
| LMArena Vision | 1248 | 1195 |
| VPCT | — | 45% |

## Multilingual

- ERNIE 5.0 0110: 54.3 (#47)
- GPT-4.5: 52.7 (#78)

| Benchmark | ERNIE 5.0 0110 | GPT-4.5 |
|---|---|---|
| LMArena Non-English | 1436 | 1413 |
| LMArena Chinese | 1512 | 1421 |
| LMArena French | 1466 | 1417 |
| LMArena German | 1462 | 1457 |
| LMArena Japanese | 1383 | 1416 |
| LMArena Korean | 1406 | 1392 |
| LMArena Russian | 1446 | 1419 |
| LMArena Spanish | 1473 | — |

## Instruction Following

- ERNIE 5.0 0110: 74.7 (#88)
- GPT-4.5: 72.8 (#129)

| Benchmark | ERNIE 5.0 0110 | GPT-4.5 |
|---|---|---|
| LMArena Instruction Following | 1413 | 1404 |
| LiveBench Instruction Following | — | 72.3% |

## Long Context

- ERNIE 5.0 0110: 43.4 (#90)
- GPT-4.5: 40.4 (#150)

| Benchmark | ERNIE 5.0 0110 | GPT-4.5 |
|---|---|---|
| LMArena Longer Query | 1422 | 1406 |
| Fiction.LiveBench | — | 63.9% |

## Writing & Preference

- ERNIE 5.0 0110: 63.4 (#64)
- GPT-4.5: 57.1 (#129)

| Benchmark | ERNIE 5.0 0110 | GPT-4.5 |
|---|---|---|
| LMArena Text | 1445 | 1417 |
| LMArena Creative Writing | 1426 | 1394 |
| LMArena Multi-Turn | 1433 | 1444 |
| Short-Story Creative Writing | — | 75.6% |
| EQ-Bench Creative Writing | — | 1258 |
| LiveBench Language | — | 61.5% |

## FAQ

### Is ERNIE 5.0 0110 better than GPT-4.5?

ERNIE 5.0 0110 is the stronger model overall, scoring 41.2 to 36.9 on the Noometry Index.

### Is ERNIE 5.0 0110 or GPT-4.5 better for coding?

They score almost the same on coding (42.3 vs 41.8); test both on your own repository before choosing.

### How many benchmarks do ERNIE 5.0 0110 and GPT-4.5 share?

17 benchmarks have published results for both models. ERNIE 5.0 0110 has 20 scored results on Noometry and GPT-4.5 has 42.