Model comparison
ERNIE 5.1 vs Grok 4.20 Multi-Agent
Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 43.8 on the Noometry Index.
Last verified . 19 shared benchmarks.
BaiduSummary
- They share 19 benchmarks with published results for both. ERNIE 5.1 scores higher in 7 categories and Grok 4.20 Multi-Agent in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 Multi-Agent leads 43.9 to 21.9.
- The biggest single-benchmark swing is NYT Connections (extended): 23.4% for ERNIE 5.1 and 89.6% for Grok 4.20 Multi-Agent.
Side by side
| ERNIE 5.1 | Grok 4.20 Multi-Agent | |
|---|---|---|
| Provider | Baidu | xAI |
| Noometry Index | 43.8 | 46.2 |
| Released | — | 2026-03-09 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 30K |
| Input $ / M tokens | — | $1.25 |
| Output $ / M tokens | — | $2.50 |
| Results tracked | 19 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
ERNIE 5.1: 44.0 (#76), Grok 4.20 Multi-Agent: 43.0 (#92)
| Benchmark | ERNIE 5.1 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Coding | 1488 | 1457 |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, Grok 4.20 Multi-Agent: —
| Benchmark | ERNIE 5.1 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Search | 1227 | 1204 |
Reasoning Grok 4.20 Multi-Agent leads
ERNIE 5.1: 21.9 (#211), Grok 4.20 Multi-Agent: 43.9 (#48)
| Benchmark | ERNIE 5.1 | Grok 4.20 Multi-Agent |
|---|---|---|
| NYT Connections (extended) | 23.4% | 89.6% |
| LMArena Hard Prompts | 1481 | 1448 |
Math Too close to call
ERNIE 5.1: 40.3 (#92), Grok 4.20 Multi-Agent: 39.4 (#104)
| Benchmark | ERNIE 5.1 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Math | 1481 | 1442 |
Knowledge ERNIE 5.1 leads
ERNIE 5.1: 41.9 (#102), Grok 4.20 Multi-Agent: 40.4 (#119)
| Benchmark | ERNIE 5.1 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Expert | 1492 | 1445 |
Multimodal Not comparable
ERNIE 5.1: —, Grok 4.20 Multi-Agent: 40.5 (#48)
| Benchmark | ERNIE 5.1 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Vision | — | 1259 |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.5 (#29), Grok 4.20 Multi-Agent: 54.4 (#43)
| Benchmark | ERNIE 5.1 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Non-English | 1454 | 1440 |
| LMArena Chinese | 1508 | 1475 |
| LMArena French | 1488 | 1466 |
| LMArena German | 1470 | 1456 |
| LMArena Japanese | 1422 | 1405 |
| LMArena Korean | 1427 | 1416 |
| LMArena Russian | 1459 | 1457 |
| LMArena Spanish | 1473 | 1447 |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.7 (#37), Grok 4.20 Multi-Agent: 74.8 (#84)
| Benchmark | ERNIE 5.1 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Instruction Following | 1460 | 1420 |
Long Context ERNIE 5.1 leads
ERNIE 5.1: 44.7 (#59), Grok 4.20 Multi-Agent: 43.7 (#88)
| Benchmark | ERNIE 5.1 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Longer Query | 1462 | 1431 |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.1 (#52), Grok 4.20 Multi-Agent: 64.0 (#59)
| Benchmark | ERNIE 5.1 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Text | 1468 | 1450 |
| LMArena Creative Writing | 1441 | 1436 |
| LMArena Multi-Turn | 1471 | 1452 |
Frequently asked questions
Is ERNIE 5.1 better than Grok 4.20 Multi-Agent?
Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 43.8 on the Noometry Index.
Is ERNIE 5.1 or Grok 4.20 Multi-Agent better for coding?
They score almost the same on coding (44.0 vs 43.0); test both on your own repository before choosing.
How many benchmarks do ERNIE 5.1 and Grok 4.20 Multi-Agent share?
19 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Grok 4.20 Multi-Agent has 20.