Model comparison
ERNIE 5.1 vs Qwen3.5 27B
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 41.9 on the Noometry Index.
Last verified . 18 shared benchmarks.
Baidu
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. ERNIE 5.1 scores higher in 7 categories and Qwen3.5 27B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.1 to 59.3.
- The biggest single-benchmark swing is NYT Connections (extended): 23.4% for ERNIE 5.1 and 47.9% for Qwen3.5 27B.
- Qwen3.5 27B has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.1 | Qwen3.5 27B | |
|---|---|---|
| Provider | Baidu | Alibaba (Qwen) |
| Noometry Index | 43.8 | 41.9 |
| Released | — | 2026-02-23 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $2.40 |
| Results tracked | 19 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding ERNIE 5.1 leads
ERNIE 5.1: 44.0 (#76), Qwen3.5 27B: 38.9 (#168)
| Benchmark | ERNIE 5.1 | Qwen3.5 27B |
|---|---|---|
| LMArena Coding | 1488 | 1427 |
| LMArena WebDev | — | 1358 |
| WeirdML | — | 39.5% |
| ALE-Bench | — | 349.45 |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, Qwen3.5 27B: —
| Benchmark | ERNIE 5.1 | Qwen3.5 27B |
|---|---|---|
| LMArena Search | 1227 | — |
| Vending-Bench 2 | — | 201.98 |
Reasoning Qwen3.5 27B leads
ERNIE 5.1: 21.9 (#211), Qwen3.5 27B: 27.5 (#117)
| Benchmark | ERNIE 5.1 | Qwen3.5 27B |
|---|---|---|
| NYT Connections (extended) | 23.4% | 47.9% |
| LMArena Hard Prompts | 1481 | 1414 |
| Thematic Generalization | — | 45.5% |
| DTBench | — | 82.4% |
| LMCA | — | 34% |
Math ERNIE 5.1 leads
ERNIE 5.1: 40.3 (#92), Qwen3.5 27B: 38.8 (#127)
| Benchmark | ERNIE 5.1 | Qwen3.5 27B |
|---|---|---|
| LMArena Math | 1481 | 1429 |
| MathArena Final-Answer Competitions | — | 56.7% |
Knowledge ERNIE 5.1 leads
ERNIE 5.1: 41.9 (#102), Qwen3.5 27B: 38.0 (#150)
| Benchmark | ERNIE 5.1 | Qwen3.5 27B |
|---|---|---|
| LMArena Expert | 1492 | 1428 |
| Vectara Hallucination Rate | — | 12.1% |
Multimodal Not comparable
ERNIE 5.1: —, Qwen3.5 27B: 39.4 (#59)
| Benchmark | ERNIE 5.1 | Qwen3.5 27B |
|---|---|---|
| LMArena Vision | — | 1241 |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.5 (#29), Qwen3.5 27B: 50.8 (#115)
| Benchmark | ERNIE 5.1 | Qwen3.5 27B |
|---|---|---|
| LMArena Non-English | 1454 | 1390 |
| LMArena Chinese | 1508 | 1478 |
| LMArena French | 1488 | 1410 |
| LMArena German | 1470 | 1393 |
| LMArena Japanese | 1422 | 1345 |
| LMArena Korean | 1427 | 1358 |
| LMArena Russian | 1459 | 1390 |
| LMArena Spanish | 1473 | 1407 |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.7 (#37), Qwen3.5 27B: 73.5 (#119)
| Benchmark | ERNIE 5.1 | Qwen3.5 27B |
|---|---|---|
| LMArena Instruction Following | 1460 | 1393 |
Long Context ERNIE 5.1 leads
ERNIE 5.1: 44.7 (#59), Qwen3.5 27B: 43.1 (#106)
| Benchmark | ERNIE 5.1 | Qwen3.5 27B |
|---|---|---|
| LMArena Longer Query | 1462 | 1413 |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.1 (#52), Qwen3.5 27B: 59.3 (#111)
| Benchmark | ERNIE 5.1 | Qwen3.5 27B |
|---|---|---|
| LMArena Text | 1468 | 1409 |
| LMArena Creative Writing | 1441 | 1362 |
| LMArena Multi-Turn | 1471 | 1410 |
Frequently asked questions
Is ERNIE 5.1 better than Qwen3.5 27B?
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 41.9 on the Noometry Index.
Is ERNIE 5.1 or Qwen3.5 27B better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 38.9 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and Qwen3.5 27B share?
18 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Qwen3.5 27B has 28.