Model comparison
ERNIE 5.1 vs Granite 3.1 2b Instruct
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 33.2 on the Noometry Index.
Last verified . 12 shared benchmarks.
BaiduSummary
- They share 12 benchmarks with published results for both. ERNIE 5.1 scores higher in 7 categories and Granite 3.1 2b Instruct 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 34.1.
- Granite 3.1 2b Instruct has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.1 | Granite 3.1 2b Instruct | |
|---|---|---|
| Provider | Baidu | IBM |
| Noometry Index | 43.8 | 33.2 |
| Released | — | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 12 |
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), Granite 3.1 2b Instruct: 33.4 (#257)
| Benchmark | ERNIE 5.1 | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Coding | 1488 | 1149 |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, Granite 3.1 2b Instruct: —
| Benchmark | ERNIE 5.1 | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Search | 1227 | — |
Reasoning Too close to call
ERNIE 5.1: 21.9 (#211), Granite 3.1 2b Instruct: 22.0 (#209)
| Benchmark | ERNIE 5.1 | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1138 |
| NYT Connections (extended) | 23.4% | — |
Math ERNIE 5.1 leads
ERNIE 5.1: 40.3 (#92), Granite 3.1 2b Instruct: 33.1 (#206)
| Benchmark | ERNIE 5.1 | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Math | 1481 | 1159 |
Knowledge ERNIE 5.1 leads
ERNIE 5.1: 41.9 (#102), Granite 3.1 2b Instruct: 30.8 (#224)
| Benchmark | ERNIE 5.1 | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Expert | 1492 | 1131 |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.5 (#29), Granite 3.1 2b Instruct: 29.1 (#269)
| Benchmark | ERNIE 5.1 | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Non-English | 1454 | 1068 |
| LMArena Chinese | 1508 | 1139 |
| LMArena Russian | 1459 | 1063 |
| 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), Granite 3.1 2b Instruct: 57.7 (#264)
| Benchmark | ERNIE 5.1 | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Instruction Following | 1460 | 1116 |
Long Context ERNIE 5.1 leads
ERNIE 5.1: 44.7 (#59), Granite 3.1 2b Instruct: 35.0 (#244)
| Benchmark | ERNIE 5.1 | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Longer Query | 1462 | 1155 |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.1 (#52), Granite 3.1 2b Instruct: 34.1 (#274)
| Benchmark | ERNIE 5.1 | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Text | 1468 | 1127 |
| LMArena Creative Writing | 1441 | 1116 |
| LMArena Multi-Turn | 1471 | 1099 |
Frequently asked questions
Is ERNIE 5.1 better than Granite 3.1 2b Instruct?
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 33.2 on the Noometry Index.
Is ERNIE 5.1 or Granite 3.1 2b Instruct better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 33.4 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and Granite 3.1 2b Instruct share?
12 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Granite 3.1 2b Instruct has 12.