Model comparison
ERNIE 5.1 vs Qwen3-4B
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 31.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
Baidu
Alibaba (Qwen)Summary
- The widest gap is in math, where ERNIE 5.1 leads 40.3 to 29.7.
- Qwen3-4B has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.1 | Qwen3-4B | |
|---|---|---|
| Provider | Baidu | Alibaba (Qwen) |
| Noometry Index | 43.8 | 31.9 |
| Released | — | 2025-04-29 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
ERNIE 5.1: 44.0 (#76), Qwen3-4B: —
| Benchmark | ERNIE 5.1 | Qwen3-4B |
|---|---|---|
| LMArena Coding | 1488 | — |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, Qwen3-4B: 27.6 (#100)
| Benchmark | ERNIE 5.1 | Qwen3-4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 35.7% |
| LMArena Search | 1227 | — |
Reasoning ERNIE 5.1 leads
ERNIE 5.1: 21.9 (#211), Qwen3-4B: 19.2 (#268)
| Benchmark | ERNIE 5.1 | Qwen3-4B |
|---|---|---|
| NYT Connections (extended) | 23.4% | — |
| Chess Puzzles | — | 4% |
| LMArena Hard Prompts | 1481 | — |
Math ERNIE 5.1 leads
ERNIE 5.1: 40.3 (#92), Qwen3-4B: 29.7 (#240)
| Benchmark | ERNIE 5.1 | Qwen3-4B |
|---|---|---|
| MathArena Final-Answer Competitions | — | 38.5% |
| OTIS Mock AIME 2024-2025 | — | 52.2% |
| LMArena Math | 1481 | — |
Knowledge ERNIE 5.1 leads
ERNIE 5.1: 41.9 (#102), Qwen3-4B: 33.0 (#208)
| Benchmark | ERNIE 5.1 | Qwen3-4B |
|---|---|---|
| GPQA Diamond | — | 52.3% |
| Vectara Hallucination Rate | — | 5.7% |
| LMArena Expert | 1492 | — |
Multilingual Not comparable
ERNIE 5.1: 55.5 (#29), Qwen3-4B: —
| Benchmark | ERNIE 5.1 | Qwen3-4B |
|---|---|---|
| LMArena Non-English | 1454 | — |
| LMArena Chinese | 1508 | — |
| LMArena French | 1488 | — |
| LMArena German | 1470 | — |
| LMArena Japanese | 1422 | — |
| LMArena Korean | 1427 | — |
| LMArena Russian | 1459 | — |
| LMArena Spanish | 1473 | — |
Instruction Following Not comparable
ERNIE 5.1: 76.7 (#37), Qwen3-4B: —
| Benchmark | ERNIE 5.1 | Qwen3-4B |
|---|---|---|
| LMArena Instruction Following | 1460 | — |
Long Context Not comparable
ERNIE 5.1: 44.7 (#59), Qwen3-4B: —
| Benchmark | ERNIE 5.1 | Qwen3-4B |
|---|---|---|
| LMArena Longer Query | 1462 | — |
Writing & Preference Not comparable
ERNIE 5.1: 65.1 (#52), Qwen3-4B: —
| Benchmark | ERNIE 5.1 | Qwen3-4B |
|---|---|---|
| LMArena Text | 1468 | — |
| LMArena Creative Writing | 1441 | — |
| LMArena Multi-Turn | 1471 | — |
Frequently asked questions
Is ERNIE 5.1 better than Qwen3-4B?
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 31.9 on the Noometry Index.
How many benchmarks do ERNIE 5.1 and Qwen3-4B share?
0 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Qwen3-4B has 6.