Model comparison
ERNIE 5.1 vs MiniMax-M2.7
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 37.7 on the Noometry Index.
Last verified . 18 shared benchmarks.
Baidu
MiniMaxSummary
- They share 18 benchmarks with published results for both. ERNIE 5.1 scores higher in 8 categories and MiniMax-M2.7 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where ERNIE 5.1 leads 40.3 to 25.9.
- MiniMax-M2.7 has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.1 | MiniMax-M2.7 | |
|---|---|---|
| Provider | Baidu | MiniMax |
| Noometry Index | 43.8 | 37.7 |
| Released | — | 2026-03-18 |
| Weights | Proprietary | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 19 | 30 |
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), MiniMax-M2.7: 41.8 (#120)
| Benchmark | ERNIE 5.1 | MiniMax-M2.7 |
|---|---|---|
| LMArena Coding | 1488 | 1454 |
| LMArena WebDev | — | 1398 |
| SciCode | — | 47% |
| WeirdML | — | 37% |
| ALE-Bench | — | 599.25 |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, MiniMax-M2.7: 25.1 (#111)
| Benchmark | ERNIE 5.1 | MiniMax-M2.7 |
|---|---|---|
| Terminal-Bench | — | 45.1% |
| ExploitBench | — | 13.3% |
| GBAEval | — | 0% |
| LMArena Search | 1227 | — |
Reasoning ERNIE 5.1 leads
ERNIE 5.1: 21.9 (#211), MiniMax-M2.7: 19.7 (#253)
| Benchmark | ERNIE 5.1 | MiniMax-M2.7 |
|---|---|---|
| NYT Connections (extended) | 23.4% | 24.7% |
| LMArena Hard Prompts | 1481 | 1422 |
| CritPt | — | 0.6% |
| Thematic Generalization | — | 39.3% |
| Epoch Capabilities Index | — | 145.85 |
Math ERNIE 5.1 leads
ERNIE 5.1: 40.3 (#92), MiniMax-M2.7: 25.9 (#263)
| Benchmark | ERNIE 5.1 | MiniMax-M2.7 |
|---|---|---|
| LMArena Math | 1481 | 1420 |
| ProofBench | — | 3% |
Knowledge ERNIE 5.1 leads
ERNIE 5.1: 41.9 (#102), MiniMax-M2.7: 37.7 (#152)
| Benchmark | ERNIE 5.1 | MiniMax-M2.7 |
|---|---|---|
| LMArena Expert | 1492 | 1444 |
| Vectara Hallucination Rate | — | 12.9% |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.5 (#29), MiniMax-M2.7: 50.3 (#123)
| Benchmark | ERNIE 5.1 | MiniMax-M2.7 |
|---|---|---|
| LMArena Non-English | 1454 | 1382 |
| LMArena Chinese | 1508 | 1441 |
| LMArena French | 1488 | 1421 |
| LMArena German | 1470 | 1398 |
| LMArena Japanese | 1422 | 1262 |
| LMArena Korean | 1427 | 1313 |
| LMArena Russian | 1459 | 1383 |
| LMArena Spanish | 1473 | 1403 |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.7 (#37), MiniMax-M2.7: 74.1 (#103)
| Benchmark | ERNIE 5.1 | MiniMax-M2.7 |
|---|---|---|
| LMArena Instruction Following | 1460 | 1405 |
Long Context ERNIE 5.1 leads
ERNIE 5.1: 44.7 (#59), MiniMax-M2.7: 43.3 (#99)
| Benchmark | ERNIE 5.1 | MiniMax-M2.7 |
|---|---|---|
| LMArena Longer Query | 1462 | 1419 |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.1 (#52), MiniMax-M2.7: 58.9 (#112)
| Benchmark | ERNIE 5.1 | MiniMax-M2.7 |
|---|---|---|
| LMArena Text | 1468 | 1405 |
| LMArena Creative Writing | 1441 | 1354 |
| LMArena Multi-Turn | 1471 | 1412 |
Frequently asked questions
Is ERNIE 5.1 better than MiniMax-M2.7?
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 37.7 on the Noometry Index.
Is ERNIE 5.1 or MiniMax-M2.7 better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 41.8 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and MiniMax-M2.7 share?
18 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and MiniMax-M2.7 has 30.