Model comparison
ERNIE 5.1 vs Qwen3.8 Max
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 43.8 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 0 categories and Qwen3.8 Max in 8 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.2 to 40.3.
- The biggest single-benchmark swing is NYT Connections (extended): 23.4% for ERNIE 5.1 and 88.3% for Qwen3.8 Max.
Side by side
| ERNIE 5.1 | Qwen3.8 Max | |
|---|---|---|
| Provider | Baidu | Alibaba (Qwen) |
| Noometry Index | 43.8 | 56.8 |
| Released | — | 2026-08-02 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 131K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 19 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 Max leads
ERNIE 5.1: 44.0 (#76), Qwen3.8 Max: 53.5 (#29)
| Benchmark | ERNIE 5.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Coding | 1488 | 1502 |
| DeepSWE | — | 57.5% |
| LMArena WebDev | — | 1674 |
| FrontierSWE | — | 17.8% |
| SciCode | — | 53.2% |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, Qwen3.8 Max: 45.4 (#14)
| Benchmark | ERNIE 5.1 | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |
| LMArena Search | 1227 | — |
Reasoning Qwen3.8 Max leads
ERNIE 5.1: 21.9 (#211), Qwen3.8 Max: 54.4 (#26)
| Benchmark | ERNIE 5.1 | Qwen3.8 Max |
|---|---|---|
| NYT Connections (extended) | 23.4% | 88.3% |
| LMArena Hard Prompts | 1481 | 1496 |
| CritPt | — | 20% |
| Chess Puzzles | — | 40% |
| Mystery Game Puzzles | — | 38% |
| DTBench | — | 92% |
| LMCA | — | 46.2% |
| Epoch Capabilities Index | — | 156.41 |
Math Qwen3.8 Max leads
ERNIE 5.1: 40.3 (#92), Qwen3.8 Max: 73.2 (#20)
| Benchmark | ERNIE 5.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Math | 1481 | 1499 |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 58% |
Knowledge Qwen3.8 Max leads
ERNIE 5.1: 41.9 (#102), Qwen3.8 Max: 61.7 (#27)
| Benchmark | ERNIE 5.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Expert | 1492 | 1507 |
| GPQA Diamond | — | 92.7% |
| SimpleQA Verified | — | 47.3% |
Multimodal Not comparable
ERNIE 5.1: —, Qwen3.8 Max: 37.2 (#75)
| Benchmark | ERNIE 5.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |
Multilingual Qwen3.8 Max leads
ERNIE 5.1: 55.5 (#29), Qwen3.8 Max: 56.7 (#18)
| Benchmark | ERNIE 5.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1454 | 1472 |
| LMArena Chinese | 1508 | 1538 |
| LMArena French | 1488 | 1503 |
| LMArena German | 1470 | 1483 |
| LMArena Japanese | 1422 | 1467 |
| LMArena Korean | 1427 | 1461 |
| LMArena Russian | 1459 | 1481 |
| LMArena Spanish | 1473 | 1492 |
Instruction Following Too close to call
ERNIE 5.1: 76.7 (#37), Qwen3.8 Max: 77.6 (#17)
| Benchmark | ERNIE 5.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1460 | 1479 |
Long Context Too close to call
ERNIE 5.1: 44.7 (#59), Qwen3.8 Max: 45.6 (#31)
| Benchmark | ERNIE 5.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1462 | 1489 |
Writing & Preference Qwen3.8 Max leads
ERNIE 5.1: 65.1 (#52), Qwen3.8 Max: 67.1 (#30)
| Benchmark | ERNIE 5.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1468 | 1483 |
| LMArena Creative Writing | 1441 | 1479 |
| LMArena Multi-Turn | 1471 | 1489 |
Frequently asked questions
Is ERNIE 5.1 better than Qwen3.8 Max?
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 43.8 on the Noometry Index.
Is ERNIE 5.1 or Qwen3.8 Max better for coding?
Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 44.0 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and Qwen3.8 Max share?
18 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Qwen3.8 Max has 39.