Model comparison
ERNIE 5.1 vs GLM-5
GLM-5 is the stronger model overall, scoring 46.1 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 3 categories and GLM-5 in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5 leads 52.3 to 41.9.
- The biggest single-benchmark swing is NYT Connections (extended): 23.4% for ERNIE 5.1 and 74.8% for GLM-5.
- GLM-5 has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.1 | GLM-5 | |
|---|---|---|
| Provider | Baidu | Z.ai (Zhipu) |
| Noometry Index | 43.8 | 46.1 |
| Released | — | 2026-02-11 |
| Weights | Proprietary | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $3.20 |
| Results tracked | 19 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
ERNIE 5.1: 44.0 (#76), GLM-5: 49.0 (#52)
| Benchmark | ERNIE 5.1 | GLM-5 |
|---|---|---|
| LMArena Coding | 1488 | 1461 |
| SWE-bench Verified | — | 72.1% |
| SWE-bench Verified (bash only) | — | 72.8% |
| LMArena WebDev | — | 1434 |
| SWE-bench Multilingual | — | 69.7% |
| WeirdML | — | 48.2% |
| ALE-Bench | — | 765.62 |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, GLM-5: 31.1 (#71)
| Benchmark | ERNIE 5.1 | GLM-5 |
|---|---|---|
| Terminal-Bench | — | 52.4% |
| τ²-bench Airline | — | 82.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 73.7% |
| τ²-bench Telecom | — | 86.8% |
| LMArena Search | 1227 | — |
| Vending-Bench 2 | — | 4,432 |
Reasoning GLM-5 leads
ERNIE 5.1: 21.9 (#211), GLM-5: 27.6 (#116)
| Benchmark | ERNIE 5.1 | GLM-5 |
|---|---|---|
| NYT Connections (extended) | 23.4% | 74.8% |
| LMArena Hard Prompts | 1481 | 1452 |
| ARC-AGI-2 | — | 4.9% |
| SimpleBench | — | 53.2% |
| Kagi LLM Benchmark | — | 75% |
| ARC-AGI-1 | — | 44.7% |
| Chess Puzzles | — | 10% |
| Epoch Capabilities Index | — | 145.83 |
| ForecastBench | — | 61 |
Math GLM-5 leads
ERNIE 5.1: 40.3 (#92), GLM-5: 46.4 (#71)
| Benchmark | ERNIE 5.1 | GLM-5 |
|---|---|---|
| LMArena Math | 1481 | 1440 |
| MathArena Final-Answer Competitions | — | 65.7% |
| OTIS Mock AIME 2024-2025 | — | 80% |
| FrontierMath (Feb 2025 set) | — | 16.4% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge GLM-5 leads
ERNIE 5.1: 41.9 (#102), GLM-5: 52.3 (#64)
| Benchmark | ERNIE 5.1 | GLM-5 |
|---|---|---|
| LMArena Expert | 1492 | 1454 |
| GPQA Diamond | — | 87.8% |
| Vectara Hallucination Rate | — | 10.1% |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.5 (#29), GLM-5: 53.7 (#58)
| Benchmark | ERNIE 5.1 | GLM-5 |
|---|---|---|
| LMArena Non-English | 1454 | 1430 |
| LMArena Chinese | 1508 | 1511 |
| LMArena French | 1488 | 1455 |
| LMArena German | 1470 | 1445 |
| LMArena Japanese | 1422 | 1416 |
| LMArena Korean | 1427 | 1423 |
| LMArena Russian | 1459 | 1436 |
| LMArena Spanish | 1473 | 1454 |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.7 (#37), GLM-5: 75.2 (#67)
| Benchmark | ERNIE 5.1 | GLM-5 |
|---|---|---|
| LMArena Instruction Following | 1460 | 1428 |
Long Context Too close to call
ERNIE 5.1: 44.7 (#59), GLM-5: 44.7 (#60)
| Benchmark | ERNIE 5.1 | GLM-5 |
|---|---|---|
| LMArena Longer Query | 1462 | 1446 |
| CL-bench | — | 18.7% |
Writing & Preference Too close to call
ERNIE 5.1: 65.1 (#52), GLM-5: 66.0 (#38)
| Benchmark | ERNIE 5.1 | GLM-5 |
|---|---|---|
| LMArena Text | 1468 | 1446 |
| LMArena Creative Writing | 1441 | 1439 |
| LMArena Multi-Turn | 1471 | 1456 |
| EQ-Bench Creative Writing | — | 1601 |
Frequently asked questions
Is ERNIE 5.1 better than GLM-5?
GLM-5 is the stronger model overall, scoring 46.1 to 43.8 on the Noometry Index.
Is ERNIE 5.1 or GLM-5 better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 44.0 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and GLM-5 share?
18 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and GLM-5 has 45.