Model comparison

ERNIE 5.0 0110 vs Qwen3-4B

ERNIE 5.0 0110 is the stronger model overall, scoring 41.2 to 31.5 on the Noometry Index.

Last verified October 10, 2026. 0 shared benchmarks.

ERNIE 5.0 0110

Baidu

41.2

Rank #129 Confirmed

Qwen3-4B

Alibaba (Qwen)

31.5

Rank #261 Confirmed

Summary

The widest gap is in math, where ERNIE 5.0 0110 leads 36.5 to 28.5.
Qwen3-4B has downloadable open weights; the other is API-only.

Side by side

ERNIE 5.0 0110 and Qwen3-4B specifications
	ERNIE 5.0 0110	Qwen3-4B
Provider	Baidu	Alibaba (Qwen)
Noometry Index	41.2	31.5
Released	—	2025-04-29
Weights	Proprietary	Open
Context window	—	—
Max output	—	—
Input $ / M tokens	—	—
Output $ / M tokens	—	—
Results tracked	20	6

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Not comparable

ERNIE 5.0 0110: 42.3 (#94), Qwen3-4B: —

Coding benchmarks
Benchmark	ERNIE 5.0 0110	Qwen3-4B
LMArena Coding	1455	—

Agentic & Tool Use Not comparable

ERNIE 5.0 0110: —, Qwen3-4B: 27.3 (#94)

Agentic & Tool Use benchmarks
Benchmark	ERNIE 5.0 0110	Qwen3-4B
Berkeley Function Calling Leaderboard	—	35.7%

Reasoning Qwen3-4B leads

ERNIE 5.0 0110: 16.3 (#296), Qwen3-4B: 18.5 (#264)

Reasoning benchmarks
Benchmark	ERNIE 5.0 0110	Qwen3-4B
NYT Connections (extended)	10.3%	—
Chess Puzzles	—	4%
Thematic Generalization	41.7%	—
LMArena Hard Prompts	1446	—

Math ERNIE 5.0 0110 leads

ERNIE 5.0 0110: 36.5 (#111), Qwen3-4B: 28.5 (#228)

Math benchmarks
Benchmark	ERNIE 5.0 0110	Qwen3-4B
MathArena Final-Answer Competitions	—	38.5%
OTIS Mock AIME 2024-2025	—	52.2%
LMArena Math	1437	—

Knowledge ERNIE 5.0 0110 leads

ERNIE 5.0 0110: 39.2 (#125), Qwen3-4B: 33.0 (#198)

Knowledge benchmarks
Benchmark	ERNIE 5.0 0110	Qwen3-4B
GPQA Diamond	—	52.3%
Vectara Hallucination Rate	—	5.7%
LMArena Expert	1427	—

Multimodal Not comparable

ERNIE 5.0 0110: 39.1 (#49), Qwen3-4B: —

Multimodal benchmarks
Benchmark	ERNIE 5.0 0110	Qwen3-4B
LMArena Vision	1248	—

Multilingual Not comparable

ERNIE 5.0 0110: 54.3 (#47), Qwen3-4B: —

Multilingual benchmarks
Benchmark	ERNIE 5.0 0110	Qwen3-4B
LMArena Non-English	1436	—
LMArena Chinese	1512	—
LMArena French	1466	—
LMArena German	1462	—
LMArena Japanese	1383	—
LMArena Korean	1406	—
LMArena Russian	1446	—
LMArena Spanish	1473	—

Instruction Following Not comparable

ERNIE 5.0 0110: 74.7 (#88), Qwen3-4B: —

Instruction Following benchmarks
Benchmark	ERNIE 5.0 0110	Qwen3-4B
LMArena Instruction Following	1413	—

Long Context Not comparable

ERNIE 5.0 0110: 43.4 (#90), Qwen3-4B: —

Long Context benchmarks
Benchmark	ERNIE 5.0 0110	Qwen3-4B
LMArena Longer Query	1422	—

Writing & Preference Not comparable

ERNIE 5.0 0110: 63.4 (#64), Qwen3-4B: —

Writing & Preference benchmarks
Benchmark	ERNIE 5.0 0110	Qwen3-4B
LMArena Text	1445	—
LMArena Creative Writing	1426	—
LMArena Multi-Turn	1433	—

Frequently asked questions

Is ERNIE 5.0 0110 better than Qwen3-4B?