Model comparison
ERNIE 5.1 vs Qwen3.5 Max Preview
Qwen3.5 Max Preview is the stronger model overall, scoring 44.7 to 43.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
Baidu
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. ERNIE 5.1 scores higher in 3 categories and Qwen3.5 Max Preview in 5 categories; one gap is clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.5 Max Preview leads 29.6 to 20.9.
Side by side
| ERNIE 5.1 | Qwen3.5 Max Preview | |
|---|---|---|
| Provider | Baidu | Alibaba (Qwen) |
| Noometry Index | 43.1 | 44.7 |
| Released | — | — |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
ERNIE 5.1: 43.4 (#78), Qwen3.5 Max Preview: 43.4 (#79)
| Benchmark | ERNIE 5.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Coding | 1488 | 1488 |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, Qwen3.5 Max Preview: —
| Benchmark | ERNIE 5.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Search | 1227 | — |
Reasoning Qwen3.5 Max Preview leads
ERNIE 5.1: 20.9 (#209), Qwen3.5 Max Preview: 29.6 (#81)
| Benchmark | ERNIE 5.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1483 |
| NYT Connections (extended) | 23.4% | — |
Math Too close to call
ERNIE 5.1: 37.5 (#96), Qwen3.5 Max Preview: 37.3 (#99)
| Benchmark | ERNIE 5.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Math | 1481 | 1473 |
Knowledge Too close to call
ERNIE 5.1: 41.2 (#103), Qwen3.5 Max Preview: 41.1 (#104)
| Benchmark | ERNIE 5.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Expert | 1491 | 1489 |
Multilingual Too close to call
ERNIE 5.1: 55.7 (#28), Qwen3.5 Max Preview: 56.4 (#21)
| Benchmark | ERNIE 5.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Non-English | 1455 | 1465 |
| LMArena Chinese | 1507 | 1534 |
| LMArena French | 1486 | 1483 |
| LMArena German | 1470 | 1487 |
| LMArena Japanese | 1422 | 1497 |
| LMArena Korean | 1428 | 1438 |
| LMArena Russian | 1459 | 1472 |
| LMArena Spanish | 1472 | 1470 |
Instruction Following Too close to call
ERNIE 5.1: 76.9 (#35), Qwen3.5 Max Preview: 77.2 (#28)
| Benchmark | ERNIE 5.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1460 | 1467 |
Long Context Too close to call
ERNIE 5.1: 44.7 (#56), Qwen3.5 Max Preview: 45.2 (#44)
| Benchmark | ERNIE 5.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Longer Query | 1462 | 1477 |
Writing & Preference Too close to call
ERNIE 5.1: 65.3 (#50), Qwen3.5 Max Preview: 66.1 (#39)
| Benchmark | ERNIE 5.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Text | 1468 | 1471 |
| LMArena Creative Writing | 1440 | 1464 |
| LMArena Multi-Turn | 1471 | 1478 |
Frequently asked questions
Is ERNIE 5.1 better than Qwen3.5 Max Preview?
Qwen3.5 Max Preview is the stronger model overall, scoring 44.7 to 43.1 on the Noometry Index.
Is ERNIE 5.1 or Qwen3.5 Max Preview better for coding?
They score almost the same on coding (43.4 vs 43.4); test both on your own repository before choosing.
How many benchmarks do ERNIE 5.1 and Qwen3.5 Max Preview share?
17 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Qwen3.5 Max Preview has 17.