# ERNIE 5.1 vs GPT-4o mini

> ERNIE 5.1 is the stronger model overall, scoring 43.1 to 25.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ernie-5-1-vs-gpt-4o-mini
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. ERNIE 5.1 scores higher in 8 categories and GPT-4o mini in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where ERNIE 5.1 leads 37.5 to 9.9.

## Snapshot

| | ERNIE 5.1 | GPT-4o mini |
|---|---|---|
| Provider | Baidu | OpenAI |
| Noometry Index | 43.1 | 25.4 |
| Rank | 87 | 337 |
| Context | — | 128K |
| Input $/M | — | $0.15 |
| Output $/M | — | $0.60 |
| Weights | Proprietary | Proprietary |

## Coding

- ERNIE 5.1: 43.4 (#78)
- GPT-4o mini: 21.6 (#330)

| Benchmark | ERNIE 5.1 | GPT-4o mini |
|---|---|---|
| LMArena Coding | 1488 | 1290 |
| Aider Polyglot | — | 3.6% |
| WeirdML | — | 11.8% |
| BigCodeBench Instruct | — | 46.1% |
| LiveBench Coding | — | 43.1% |
| BigCodeBench Complete | — | 57.4% |
| HumanEval+ | — | 83.5% |
| MBPP+ | — | 72.2% |

## Agentic & Tool Use

- ERNIE 5.1: —
- GPT-4o mini: 27.2 (#95)

| Benchmark | ERNIE 5.1 | GPT-4o mini |
|---|---|---|
| BALROG | — | 17.4% |
| LMArena Search | 1227 | — |

## Reasoning

- ERNIE 5.1: 20.9 (#209)
- GPT-4o mini: 8.7 (#343)

| Benchmark | ERNIE 5.1 | GPT-4o mini |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1267 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 10.7% |
| Kagi LLM Benchmark | — | 28.8% |
| NYT Connections (extended) | 23.4% | — |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 32.8% |
| Mystery Game Puzzles | — | 12% |
| DTBench | — | 54.4% |
| LiveBench Data Analysis | — | 50% |
| LMCA | — | 10.4% |
| Epoch Capabilities Index | — | 126.56 |
| LiveBench | — | 41.3% |
| PIQA | — | 88.7% |

## Math

- ERNIE 5.1: 37.5 (#96)
- GPT-4o mini: 9.9 (#307)

| Benchmark | ERNIE 5.1 | GPT-4o mini |
|---|---|---|
| LMArena Math | 1481 | 1267 |
| FrontierMath (Tiers 1-3) | — | 0.7% |
| OTIS Mock AIME 2024-2025 | — | 6.9% |
| Omni-MATH | — | 28% |
| LiveBench Math | — | 36.3% |
| MATH Level 5 | — | 52.6% |
| GSM8K | — | 91.3% |

## Knowledge

- ERNIE 5.1: 41.2 (#103)
- GPT-4o mini: 17.7 (#279)

| Benchmark | ERNIE 5.1 | GPT-4o mini |
|---|---|---|
| LMArena Expert | 1491 | 1235 |
| GPQA Diamond | — | 37.7% |
| SimpleQA Verified | — | 8.3% |
| MMLU-Pro | — | 60.3% |
| Confabulations | — | 37.2% |
| GPQA (HELM) | — | 36.8% |
| BoolQ | — | 88.7% |
| MMLU | — | 81.8% |

## Multimodal

- ERNIE 5.1: —
- GPT-4o mini: 25.3 (#117)

| Benchmark | ERNIE 5.1 | GPT-4o mini |
|---|---|---|
| LMArena Vision | — | 1066 |
| Video-MME | — | 64.8% |
| GeoBench | — | 64% |
| VPCT | — | 34% |

## Multilingual

- ERNIE 5.1: 55.7 (#28)
- GPT-4o mini: 42.2 (#194)

| Benchmark | ERNIE 5.1 | GPT-4o mini |
|---|---|---|
| LMArena Non-English | 1455 | 1266 |
| LMArena Chinese | 1507 | 1264 |
| LMArena French | 1486 | 1296 |
| LMArena German | 1470 | 1272 |
| LMArena Japanese | 1422 | 1216 |
| LMArena Korean | 1428 | 1195 |
| LMArena Russian | 1459 | 1275 |
| LMArena Spanish | 1472 | 1276 |

## Instruction Following

- ERNIE 5.1: 76.9 (#35)
- GPT-4o mini: 62.1 (#234)

| Benchmark | ERNIE 5.1 | GPT-4o mini |
|---|---|---|
| LMArena Instruction Following | 1460 | 1259 |
| LiveBench Instruction Following | — | 56.8% |
| IFEval | — | 78.2% |

## Long Context

- ERNIE 5.1: 44.7 (#56)
- GPT-4o mini: 39.1 (#181)

| Benchmark | ERNIE 5.1 | GPT-4o mini |
|---|---|---|
| LMArena Longer Query | 1462 | 1289 |

## Writing & Preference

- ERNIE 5.1: 65.3 (#50)
- GPT-4o mini: 39.7 (#243)

| Benchmark | ERNIE 5.1 | GPT-4o mini |
|---|---|---|
| LMArena Text | 1468 | 1286 |
| LMArena Creative Writing | 1440 | 1268 |
| LMArena Multi-Turn | 1471 | 1285 |
| Short-Story Creative Writing | — | 67.2% |
| EQ-Bench Creative Writing | — | 873 |
| WildBench | — | 79.1% |
| LiveBench Language | — | 28.6% |

## FAQ

### Is ERNIE 5.1 better than GPT-4o mini?

ERNIE 5.1 is the stronger model overall, scoring 43.1 to 25.4 on the Noometry Index.

### Is ERNIE 5.1 or GPT-4o mini better for coding?

ERNIE 5.1 scores higher on coding benchmarks: 43.4 versus 21.6 in the Noometry coding category.

### How many benchmarks do ERNIE 5.1 and GPT-4o mini share?

17 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and GPT-4o mini has 60.