Model comparison
ERNIE 5.1 vs GLM-4.6
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 41.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
BaiduSummary
- They share 17 benchmarks with published results for both. ERNIE 5.1 scores higher in 7 categories and GLM-4.6 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 61.1.
- GLM-4.6 has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.1 | GLM-4.6 | |
|---|---|---|
| Provider | Baidu | Z.ai (Zhipu) |
| Noometry Index | 43.8 | 41.4 |
| Released | — | 2025-09-30 |
| Weights | Proprietary | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.60 |
| Output $ / M tokens | — | $2.20 |
| Results tracked | 19 | 29 |
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), GLM-4.6: 40.1 (#148)
| Benchmark | ERNIE 5.1 | GLM-4.6 |
|---|---|---|
| LMArena Coding | 1488 | 1449 |
| SWE-bench Verified (bash only) | — | 55.4% |
| LMArena WebDev | — | 1340 |
| SciCode | — | 38.4% |
| ALE-Bench | — | 340.82 |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, GLM-4.6: 32.3 (#66)
| Benchmark | ERNIE 5.1 | GLM-4.6 |
|---|---|---|
| Terminal-Bench | — | 24.5% |
| Berkeley Function Calling Leaderboard | — | 72.4% |
| LMArena Search | 1227 | — |
Reasoning GLM-4.6 leads
ERNIE 5.1: 21.9 (#211), GLM-4.6: 23.7 (#172)
| Benchmark | ERNIE 5.1 | GLM-4.6 |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1440 |
| Kagi LLM Benchmark | — | 47.4% |
| NYT Connections (extended) | 23.4% | — |
| CritPt | — | 1.1% |
Math ERNIE 5.1 leads
ERNIE 5.1: 40.3 (#92), GLM-4.6: 39.1 (#111)
| Benchmark | ERNIE 5.1 | GLM-4.6 |
|---|---|---|
| LMArena Math | 1481 | 1432 |
| FrontierMath (Feb 2025 set) | — | 3.8% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge ERNIE 5.1 leads
ERNIE 5.1: 41.9 (#102), GLM-4.6: 40.2 (#124)
| Benchmark | ERNIE 5.1 | GLM-4.6 |
|---|---|---|
| LMArena Expert | 1492 | 1431 |
| Vectara Hallucination Rate | — | 9.5% |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.5 (#29), GLM-4.6: 53.5 (#66)
| Benchmark | ERNIE 5.1 | GLM-4.6 |
|---|---|---|
| LMArena Non-English | 1454 | 1426 |
| LMArena Chinese | 1508 | 1499 |
| LMArena French | 1488 | 1459 |
| LMArena German | 1470 | 1447 |
| LMArena Japanese | 1422 | 1393 |
| LMArena Korean | 1427 | 1400 |
| LMArena Russian | 1459 | 1419 |
| LMArena Spanish | 1473 | 1436 |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.7 (#37), GLM-4.6: 74.3 (#98)
| Benchmark | ERNIE 5.1 | GLM-4.6 |
|---|---|---|
| LMArena Instruction Following | 1460 | 1410 |
Long Context ERNIE 5.1 leads
ERNIE 5.1: 44.7 (#59), GLM-4.6: 43.4 (#94)
| Benchmark | ERNIE 5.1 | GLM-4.6 |
|---|---|---|
| LMArena Longer Query | 1462 | 1422 |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.1 (#52), GLM-4.6: 61.1 (#90)
| Benchmark | ERNIE 5.1 | GLM-4.6 |
|---|---|---|
| LMArena Text | 1468 | 1440 |
| LMArena Creative Writing | 1441 | 1411 |
| LMArena Multi-Turn | 1471 | 1427 |
| EQ-Bench Creative Writing | — | 1411 |
Frequently asked questions
Is ERNIE 5.1 better than GLM-4.6?
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 41.4 on the Noometry Index.
Is ERNIE 5.1 or GLM-4.6 better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 40.1 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and GLM-4.6 share?
17 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and GLM-4.6 has 29.