# DeepSeek V4 Flash vs ERNIE 5.0 0110

> DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 41.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v4-flash-vs-ernie-5-0
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 7 categories and ERNIE 5.0 0110 in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Flash leads 53.7 to 17.0.
- The biggest single-benchmark swing is NYT Connections (extended): 89.6% for DeepSeek V4 Flash and 10.3% for ERNIE 5.0 0110.
- DeepSeek V4 Flash has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek V4 Flash | ERNIE 5.0 0110 |
|---|---|---|
| Provider | DeepSeek | Baidu |
| Noometry Index | 53.6 | 41.8 |
| Rank | 35 | 129 |
| Context | 1M | — |
| Input $/M | $0.15 | — |
| Output $/M | $0.60 | — |
| Weights | Open | Proprietary |

## Coding

- DeepSeek V4 Flash: 47.9 (#59)
- ERNIE 5.0 0110: 43.0 (#94)

| Benchmark | DeepSeek V4 Flash | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Coding | 1457 | 1455 |
| FrontierCode | 18.8% | — |
| LMArena WebDev | 1582 | — |
| SciCode | 49.9% | — |
| WeirdML | 63% | — |
| ALE-Bench | 1,306 | — |

## Reasoning

- DeepSeek V4 Flash: 53.7 (#30)
- ERNIE 5.0 0110: 17.0 (#297)

| Benchmark | DeepSeek V4 Flash | ERNIE 5.0 0110 |
|---|---|---|
| NYT Connections (extended) | 89.6% | 10.3% |
| LMArena Hard Prompts | 1444 | 1445 |
| ARC-AGI-2 | 61.4% | — |
| SimpleBench | 61.1% | — |
| Kagi LLM Benchmark | 52.2% | — |
| ARC-AGI-1 | 89% | — |
| CritPt | 16.6% | — |
| Chess Puzzles | 33% | — |
| Thematic Generalization | — | 41.7% |
| Mystery Game Puzzles | 34% | — |
| DTBench | 90.9% | — |
| LMCA | 41.7% | — |
| Epoch Capabilities Index | 154.49 | — |

## Math

- DeepSeek V4 Flash: 60.3 (#37)
- ERNIE 5.0 0110: 39.3 (#110)

| Benchmark | DeepSeek V4 Flash | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Math | 1427 | 1437 |
| FrontierMath (Tiers 1-3) | 57.5% | — |
| FrontierMath Tier 4 | 24.4% | — |
| MathArena Final-Answer Competitions | 76.5% | — |
| OTIS Mock AIME 2024-2025 | 94.4% | — |
| ProofBench | 56% | — |

## Knowledge

- DeepSeek V4 Flash: 55.4 (#48)
- ERNIE 5.0 0110: 39.8 (#128)

| Benchmark | DeepSeek V4 Flash | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Expert | 1441 | 1428 |
| GPQA Diamond | 91% | — |
| SimpleQA Verified | 33.6% | — |

## Multimodal

- DeepSeek V4 Flash: —
- ERNIE 5.0 0110: 39.9 (#53)

| Benchmark | DeepSeek V4 Flash | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Vision | — | 1249 |

## Multilingual

- DeepSeek V4 Flash: 53.0 (#72)
- ERNIE 5.0 0110: 54.1 (#49)

| Benchmark | DeepSeek V4 Flash | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Non-English | 1420 | 1436 |
| LMArena Chinese | 1468 | 1512 |
| LMArena French | 1439 | 1467 |
| LMArena German | 1418 | 1460 |
| LMArena Japanese | 1406 | 1382 |
| LMArena Korean | 1384 | 1406 |
| LMArena Russian | 1428 | 1446 |
| LMArena Spanish | 1436 | 1473 |

## Instruction Following

- DeepSeek V4 Flash: 74.9 (#81)
- ERNIE 5.0 0110: 74.5 (#92)

| Benchmark | DeepSeek V4 Flash | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Instruction Following | 1421 | 1413 |

## Long Context

- DeepSeek V4 Flash: 43.8 (#85)
- ERNIE 5.0 0110: 43.4 (#95)

| Benchmark | DeepSeek V4 Flash | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Longer Query | 1434 | 1422 |

## Writing & Preference

- DeepSeek V4 Flash: 63.8 (#61)
- ERNIE 5.0 0110: 63.1 (#66)

| Benchmark | DeepSeek V4 Flash | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Text | 1432 | 1445 |
| LMArena Creative Writing | 1403 | 1426 |
| LMArena Multi-Turn | 1449 | 1434 |
| EQ-Bench Creative Writing | 1559 | — |

## FAQ

### Is DeepSeek V4 Flash better than ERNIE 5.0 0110?

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 41.8 on the Noometry Index.

### Is DeepSeek V4 Flash or ERNIE 5.0 0110 better for coding?

DeepSeek V4 Flash scores higher on coding benchmarks: 47.9 versus 43.0 in the Noometry coding category.

### How many benchmarks do DeepSeek V4 Flash and ERNIE 5.0 0110 share?

18 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and ERNIE 5.0 0110 has 20.