Model comparison
ERNIE 5.1 vs Mercury 2
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 39.1 on the Noometry Index.
Last verified . 11 shared benchmarks.
BaiduSummary
- They share 11 benchmarks with published results for both. ERNIE 5.1 scores higher in 6 categories and Mercury 2 in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.1 to 53.8.
Side by side
| ERNIE 5.1 | Mercury 2 | |
|---|---|---|
| Provider | Baidu | Inception |
| Noometry Index | 43.8 | 39.1 |
| Released | — | 2026-02-20 |
| Weights | Proprietary | Proprietary |
| Context window | — | 128K |
| Max output | — | 50K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.75 |
| Results tracked | 19 | 17 |
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), Mercury 2: 33.5 (#255)
| Benchmark | ERNIE 5.1 | Mercury 2 |
|---|---|---|
| LMArena Coding | 1488 | 1391 |
| LMArena WebDev | — | 1171 |
| SciCode | — | 38.7% |
| WeirdML | — | 43.2% |
| ALE-Bench | — | 785.58 |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, Mercury 2: —
| Benchmark | ERNIE 5.1 | Mercury 2 |
|---|---|---|
| LMArena Search | 1227 | — |
Reasoning Mercury 2 leads
ERNIE 5.1: 21.9 (#211), Mercury 2: 23.8 (#170)
| Benchmark | ERNIE 5.1 | Mercury 2 |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1362 |
| NYT Connections (extended) | 23.4% | — |
| CritPt | — | 0.8% |
Math Not comparable
ERNIE 5.1: 40.3 (#92), Mercury 2: —
| Benchmark | ERNIE 5.1 | Mercury 2 |
|---|---|---|
| LMArena Math | 1481 | — |
Knowledge ERNIE 5.1 leads
ERNIE 5.1: 41.9 (#102), Mercury 2: 36.2 (#172)
| Benchmark | ERNIE 5.1 | Mercury 2 |
|---|---|---|
| LMArena Expert | 1492 | 1358 |
| Vectara Hallucination Rate | — | 12.3% |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.5 (#29), Mercury 2: 46.6 (#157)
| Benchmark | ERNIE 5.1 | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1454 | 1331 |
| LMArena Chinese | 1508 | 1417 |
| LMArena Russian | 1459 | 1304 |
| LMArena French | 1488 | — |
| LMArena German | 1470 | — |
| LMArena Japanese | 1422 | — |
| LMArena Korean | 1427 | — |
| LMArena Spanish | 1473 | — |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.7 (#37), Mercury 2: 70.2 (#165)
| Benchmark | ERNIE 5.1 | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1460 | 1329 |
Long Context ERNIE 5.1 leads
ERNIE 5.1: 44.7 (#59), Mercury 2: 40.5 (#154)
| Benchmark | ERNIE 5.1 | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1462 | 1330 |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.1 (#52), Mercury 2: 53.8 (#155)
| Benchmark | ERNIE 5.1 | Mercury 2 |
|---|---|---|
| LMArena Text | 1468 | 1355 |
| LMArena Creative Writing | 1441 | 1289 |
| LMArena Multi-Turn | 1471 | 1358 |
Frequently asked questions
Is ERNIE 5.1 better than Mercury 2?
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 39.1 on the Noometry Index.
Is ERNIE 5.1 or Mercury 2 better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 33.5 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and Mercury 2 share?
11 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Mercury 2 has 17.