Model comparison
ERNIE 5.1 vs GLM-5.1
GLM-5.1 is the stronger model overall, scoring 47.8 to 43.8 on the Noometry Index.
Last verified . 18 shared benchmarks.
BaiduSummary
- They share 18 benchmarks with published results for both. ERNIE 5.1 scores higher in 2 categories and GLM-5.1 in 6 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.1 leads 39.1 to 21.9.
- The biggest single-benchmark swing is NYT Connections (extended): 23.4% for ERNIE 5.1 and 77.7% for GLM-5.1.
- GLM-5.1 has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.1 | GLM-5.1 | |
|---|---|---|
| Provider | Baidu | Z.ai (Zhipu) |
| Noometry Index | 43.8 | 47.8 |
| Released | — | 2026-04-07 |
| Weights | Proprietary | Open |
| Context window | — | 200K |
| Max output | — | 131K |
| Input $ / M tokens | — | $1.40 |
| Output $ / M tokens | — | $4.40 |
| Results tracked | 19 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.1 leads
ERNIE 5.1: 44.0 (#76), GLM-5.1: 48.7 (#55)
| Benchmark | ERNIE 5.1 | GLM-5.1 |
|---|---|---|
| LMArena Coding | 1488 | 1485 |
| SWE-bench Verified | — | 74.2% |
| LMArena WebDev | — | 1508 |
| SciCode | — | 43.8% |
| WeirdML | — | 57.1% |
| ALE-Bench | — | 887.1 |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, GLM-5.1: 24.9 (#113)
| Benchmark | ERNIE 5.1 | GLM-5.1 |
|---|---|---|
| APEX-Agents | — | 40.9% |
| ExploitBench | — | 18.1% |
| GBAEval | — | 0% |
| LMArena Search | 1227 | — |
| Vending-Bench 2 | — | 5,634 |
Reasoning GLM-5.1 leads
ERNIE 5.1: 21.9 (#211), GLM-5.1: 39.1 (#60)
| Benchmark | ERNIE 5.1 | GLM-5.1 |
|---|---|---|
| NYT Connections (extended) | 23.4% | 77.7% |
| LMArena Hard Prompts | 1481 | 1472 |
| SimpleBench | — | 55.1% |
| CritPt | — | 4.6% |
| Chess Puzzles | — | 19% |
| Thematic Generalization | — | 69.8% |
| Epoch Capabilities Index | — | 149.84 |
Math GLM-5.1 leads
ERNIE 5.1: 40.3 (#92), GLM-5.1: 49.7 (#60)
| Benchmark | ERNIE 5.1 | GLM-5.1 |
|---|---|---|
| LMArena Math | 1481 | 1473 |
| FrontierMath (Tiers 1-3) | — | 36.8% |
| MathArena Final-Answer Competitions | — | 67.1% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| ProofBench | — | 22.2% |
| FrontierMath (Feb 2025 set) | — | 33.4% |
| FrontierMath Tier 4 (v1) | — | 12.5% |
Knowledge GLM-5.1 leads
ERNIE 5.1: 41.9 (#102), GLM-5.1: 54.9 (#50)
| Benchmark | ERNIE 5.1 | GLM-5.1 |
|---|---|---|
| LMArena Expert | 1492 | 1476 |
| GPQA Diamond | — | 89.9% |
| SimpleQA Verified | — | 34% |
Multilingual Too close to call
ERNIE 5.1: 55.5 (#29), GLM-5.1: 55.0 (#36)
| Benchmark | ERNIE 5.1 | GLM-5.1 |
|---|---|---|
| LMArena Non-English | 1454 | 1447 |
| LMArena Chinese | 1508 | 1515 |
| LMArena French | 1488 | 1474 |
| LMArena German | 1470 | 1465 |
| LMArena Japanese | 1422 | 1434 |
| LMArena Korean | 1427 | 1418 |
| LMArena Russian | 1459 | 1454 |
| LMArena Spanish | 1473 | 1469 |
Instruction Following Too close to call
ERNIE 5.1: 76.7 (#37), GLM-5.1: 76.3 (#42)
| Benchmark | ERNIE 5.1 | GLM-5.1 |
|---|---|---|
| LMArena Instruction Following | 1460 | 1451 |
Long Context Too close to call
ERNIE 5.1: 44.7 (#59), GLM-5.1: 44.9 (#53)
| Benchmark | ERNIE 5.1 | GLM-5.1 |
|---|---|---|
| LMArena Longer Query | 1462 | 1466 |
Writing & Preference GLM-5.1 leads
ERNIE 5.1: 65.1 (#52), GLM-5.1: 66.9 (#31)
| Benchmark | ERNIE 5.1 | GLM-5.1 |
|---|---|---|
| LMArena Text | 1468 | 1461 |
| LMArena Creative Writing | 1441 | 1453 |
| LMArena Multi-Turn | 1471 | 1472 |
| EQ-Bench Creative Writing | — | 1592 |
Frequently asked questions
Is ERNIE 5.1 better than GLM-5.1?
GLM-5.1 is the stronger model overall, scoring 47.8 to 43.8 on the Noometry Index.
Is ERNIE 5.1 or GLM-5.1 better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.7 versus 44.0 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and GLM-5.1 share?
18 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and GLM-5.1 has 41.