# ERNIE 5.1 vs Llama 4 Maverick

> ERNIE 5.1 is the stronger model overall, scoring 43.8 to 30.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ernie-5-1-vs-llama-4-maverick
- Last updated: 2026-10-12
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. ERNIE 5.1 scores higher in 8 categories and Llama 4 Maverick in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.1 to 38.8.
- The biggest single-benchmark swing is NYT Connections (extended): 23.4% for ERNIE 5.1 and 8% for Llama 4 Maverick.
- Llama 4 Maverick has downloadable open weights; the other is API-only.

## Snapshot

| | ERNIE 5.1 | Llama 4 Maverick |
|---|---|---|
| Provider | Baidu | Meta |
| Noometry Index | 43.8 | 30.9 |
| Rank | 83 | 282 |
| Context | — | 128K |
| Input $/M | — | $0.19 |
| Output $/M | — | $0.65 |
| Weights | Proprietary | Open |

## Coding

- ERNIE 5.1: 44.0 (#76)
- Llama 4 Maverick: 26.6 (#324)

| Benchmark | ERNIE 5.1 | Llama 4 Maverick |
|---|---|---|
| LMArena Coding | 1488 | 1302 |
| SWE-bench Verified (bash only) | — | 21% |
| Aider Polyglot | — | 15.6% |
| SciCode | — | 33.1% |
| WeirdML | — | 24.5% |
| BigCodeBench Instruct | — | 49.7% |
| BigCodeBench Complete | — | 61.4% |
| ALE-Bench | — | 172.97 |

## Agentic & Tool Use

- ERNIE 5.1: —
- Llama 4 Maverick: 28.2 (#91)

| Benchmark | ERNIE 5.1 | Llama 4 Maverick |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.3% |
| LMArena Search | 1227 | — |

## Reasoning

- ERNIE 5.1: 21.9 (#211)
- Llama 4 Maverick: 10.1 (#342)

| Benchmark | ERNIE 5.1 | Llama 4 Maverick |
|---|---|---|
| NYT Connections (extended) | 23.4% | 8% |
| LMArena Hard Prompts | 1481 | 1281 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 27.7% |
| Kagi LLM Benchmark | — | 55.9% |
| ARC-AGI-1 | — | 4.4% |
| CritPt | — | 0% |
| EnigmaEval | — | 0.6% |
| DTBench | — | 61.9% |
| LMCA | — | 15.9% |
| Epoch Capabilities Index | — | 132.2 |
| ForecastBench | — | 57.5 |

## Math

- ERNIE 5.1: 40.3 (#92)
- Llama 4 Maverick: 26.0 (#262)

| Benchmark | ERNIE 5.1 | Llama 4 Maverick |
|---|---|---|
| LMArena Math | 1481 | 1299 |
| OTIS Mock AIME 2024-2025 | — | 20.6% |
| Omni-MATH | — | 42.2% |
| MATH Level 5 | — | 73% |
| FrontierMath (Feb 2025 set) | — | 0.7% |

## Knowledge

- ERNIE 5.1: 41.9 (#102)
- Llama 4 Maverick: 33.4 (#204)

| Benchmark | ERNIE 5.1 | Llama 4 Maverick |
|---|---|---|
| LMArena Expert | 1492 | 1259 |
| GPQA Diamond | — | 67% |
| Humanity's Last Exam | — | 5.7% |
| MMLU-Pro | — | 81% |
| Confabulations | — | 22.6% |
| Vectara Hallucination Rate | — | 8.2% |
| GPQA (HELM) | — | 65% |

## Multimodal

- ERNIE 5.1: —
- Llama 4 Maverick: 31.6 (#105)

| Benchmark | ERNIE 5.1 | Llama 4 Maverick |
|---|---|---|
| LMArena Vision | — | 1142 |
| GeoBench | — | 52% |
| SpatialViz-Bench | — | 31.8% |

## Multilingual

- ERNIE 5.1: 55.5 (#29)
- Llama 4 Maverick: 42.2 (#195)

| Benchmark | ERNIE 5.1 | Llama 4 Maverick |
|---|---|---|
| LMArena Non-English | 1454 | 1269 |
| LMArena Chinese | 1508 | 1277 |
| LMArena French | 1488 | 1259 |
| LMArena German | 1470 | 1291 |
| LMArena Japanese | 1422 | 1207 |
| LMArena Korean | 1427 | 1203 |
| LMArena Russian | 1459 | 1286 |
| LMArena Spanish | 1473 | 1293 |

## Instruction Following

- ERNIE 5.1: 76.7 (#37)
- Llama 4 Maverick: 71.7 (#146)

| Benchmark | ERNIE 5.1 | Llama 4 Maverick |
|---|---|---|
| LMArena Instruction Following | 1460 | 1267 |
| IFEval | — | 90.8% |

## Long Context

- ERNIE 5.1: 44.7 (#59)
- Llama 4 Maverick: 31.4 (#279)

| Benchmark | ERNIE 5.1 | Llama 4 Maverick |
|---|---|---|
| LMArena Longer Query | 1462 | 1280 |
| Fiction.LiveBench | — | 46.2% |

## Writing & Preference

- ERNIE 5.1: 65.1 (#52)
- Llama 4 Maverick: 38.8 (#252)

| Benchmark | ERNIE 5.1 | Llama 4 Maverick |
|---|---|---|
| LMArena Text | 1468 | 1287 |
| LMArena Creative Writing | 1441 | 1267 |
| LMArena Multi-Turn | 1471 | 1289 |
| Short-Story Creative Writing | — | 62% |
| EQ-Bench Creative Writing | — | 860 |
| WildBench | — | 80% |

## FAQ

### Is ERNIE 5.1 better than Llama 4 Maverick?

ERNIE 5.1 is the stronger model overall, scoring 43.8 to 30.9 on the Noometry Index.

### Is ERNIE 5.1 or Llama 4 Maverick better for coding?

ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 26.6 in the Noometry coding category.

### How many benchmarks do ERNIE 5.1 and Llama 4 Maverick share?

18 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Llama 4 Maverick has 54.