# ERNIE 5.1 vs GPT-5 Mini

> ERNIE 5.1 is the stronger model overall, scoring 43.1 to 41.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ernie-5-1-vs-gpt-5-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 5 categories and GPT-5 Mini in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.3 to 55.4.

## Snapshot

| | ERNIE 5.1 | GPT-5 Mini |
|---|---|---|
| Provider | Baidu | OpenAI |
| Noometry Index | 43.1 | 41.7 |
| Rank | 87 | 115 |
| Context | — | 400K |
| Input $/M | — | $0.25 |
| Output $/M | — | $2 |
| Weights | Proprietary | Proprietary |

## Coding

- ERNIE 5.1: 43.4 (#78)
- GPT-5 Mini: 40.0 (#134)

| Benchmark | ERNIE 5.1 | GPT-5 Mini |
|---|---|---|
| LMArena Coding | 1488 | 1406 |
| SWE-bench Verified | — | 64.7% |
| SWE-bench Verified (bash only) | — | 59.8% |
| SWE-bench Multilingual | — | 39.7% |
| SciCode | — | 39.2% |
| WeirdML | — | 52.7% |
| ALE-Bench | — | 799.77 |
| AlgoTune | — | 1.38 |

## Agentic & Tool Use

- ERNIE 5.1: —
- GPT-5 Mini: 31.0 (#64)

| Benchmark | ERNIE 5.1 | GPT-5 Mini |
|---|---|---|
| Terminal-Bench | — | 34.8% |
| Berkeley Function Calling Leaderboard | — | 55.5% |
| LMArena Search | 1227 | — |
| Vending-Bench 2 | — | -31.18 |

## Reasoning

- ERNIE 5.1: 20.9 (#209)
- GPT-5 Mini: 24.1 (#153)

| Benchmark | ERNIE 5.1 | GPT-5 Mini |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1380 |
| ARC-AGI-2 | — | 4.4% |
| Kagi LLM Benchmark | — | 70.3% |
| NYT Connections (extended) | 23.4% | — |
| ARC-AGI-1 | — | 54.3% |
| CritPt | — | 0% |
| Chess Puzzles | — | 30% |
| EnigmaEval | — | 8.2% |
| Mystery Game Puzzles | — | 10% |
| DTBench | — | 80.5% |
| LMCA | — | 34.2% |
| Epoch Capabilities Index | — | 145.51 |
| ForecastBench | — | 61 |

## Math

- ERNIE 5.1: 37.5 (#96)
- GPT-5 Mini: 46.3 (#59)

| Benchmark | ERNIE 5.1 | GPT-5 Mini |
|---|---|---|
| LMArena Math | 1481 | 1377 |
| FrontierMath (Tiers 1-3) | — | 46.7% |
| FrontierMath Tier 4 | — | 12.2% |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| ProofBench | — | 9% |
| Omni-MATH | — | 72.2% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 27.2% |
| FrontierMath Tier 4 (v1) | — | 6.3% |

## Knowledge

- ERNIE 5.1: 41.2 (#103)
- GPT-5 Mini: 45.5 (#80)

| Benchmark | ERNIE 5.1 | GPT-5 Mini |
|---|---|---|
| LMArena Expert | 1491 | 1377 |
| GPQA Diamond | — | 75% |
| Humanity's Last Exam | — | 19.4% |
| SimpleQA Verified | — | 21.6% |
| MMLU-Pro | — | 83.5% |
| Confabulations | — | 13.3% |
| Vectara Hallucination Rate | — | 12.9% |
| GPQA (HELM) | — | 75.6% |

## Multimodal

- ERNIE 5.1: —
- GPT-5 Mini: 35.0 (#80)

| Benchmark | ERNIE 5.1 | GPT-5 Mini |
|---|---|---|
| LMArena Vision | — | 1202 |
| VPCT | — | 40.2% |

## Multilingual

- ERNIE 5.1: 55.7 (#28)
- GPT-5 Mini: 49.1 (#131)

| Benchmark | ERNIE 5.1 | GPT-5 Mini |
|---|---|---|
| LMArena Non-English | 1455 | 1363 |
| LMArena Chinese | 1507 | 1387 |
| LMArena French | 1486 | 1385 |
| LMArena German | 1470 | 1366 |
| LMArena Japanese | 1422 | 1342 |
| LMArena Korean | 1428 | 1306 |
| LMArena Russian | 1459 | 1362 |
| LMArena Spanish | 1472 | 1355 |

## Instruction Following

- ERNIE 5.1: 76.9 (#35)
- GPT-5 Mini: 76.4 (#43)

| Benchmark | ERNIE 5.1 | GPT-5 Mini |
|---|---|---|
| LMArena Instruction Following | 1460 | 1357 |
| IFEval | — | 92.7% |

## Long Context

- ERNIE 5.1: 44.7 (#56)
- GPT-5 Mini: 41.9 (#127)

| Benchmark | ERNIE 5.1 | GPT-5 Mini |
|---|---|---|
| LMArena Longer Query | 1462 | 1355 |
| Fiction.LiveBench | — | 69.4% |

## Writing & Preference

- ERNIE 5.1: 65.3 (#50)
- GPT-5 Mini: 55.4 (#143)

| Benchmark | ERNIE 5.1 | GPT-5 Mini |
|---|---|---|
| LMArena Text | 1468 | 1373 |
| LMArena Creative Writing | 1440 | 1325 |
| LMArena Multi-Turn | 1471 | 1363 |
| Short-Story Creative Writing | — | 83.1% |
| EQ-Bench Creative Writing | — | 1313 |
| WildBench | — | 85.5% |

## FAQ

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

ERNIE 5.1 is the stronger model overall, scoring 43.1 to 41.7 on the Noometry Index.

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

ERNIE 5.1 scores higher on coding benchmarks: 43.4 versus 40.0 in the Noometry coding category.

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

17 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and GPT-5 Mini has 60.