Model comparison
Codellama 70b Instruct vs ERNIE 5.1
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 33.7 on the Noometry Index.
Last verified . 4 shared benchmarks.
Meta
BaiduSummary
- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 0 categories and ERNIE 5.1 in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.1 to 33.4.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codellama 70b Instruct | ERNIE 5.1 | |
|---|---|---|
| Provider | Meta | Baidu |
| Noometry Index | 33.7 | 43.8 |
| Released | — | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding ERNIE 5.1 leads
Codellama 70b Instruct: 37.6 (#193), ERNIE 5.1: 44.0 (#76)
| Benchmark | Codellama 70b Instruct | ERNIE 5.1 |
|---|---|---|
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1488 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Agentic & Tool Use Not comparable
Codellama 70b Instruct: —, ERNIE 5.1: —
| Benchmark | Codellama 70b Instruct | ERNIE 5.1 |
|---|---|---|
| LMArena Search | — | 1227 |
Reasoning ERNIE 5.1 leads
Codellama 70b Instruct: 20.1 (#242), ERNIE 5.1: 21.9 (#211)
| Benchmark | Codellama 70b Instruct | ERNIE 5.1 |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1481 |
| NYT Connections (extended) | — | 23.4% |
Math Not comparable
Codellama 70b Instruct: —, ERNIE 5.1: 40.3 (#92)
| Benchmark | Codellama 70b Instruct | ERNIE 5.1 |
|---|---|---|
| LMArena Math | — | 1481 |
Knowledge Not comparable
Codellama 70b Instruct: —, ERNIE 5.1: 41.9 (#102)
| Benchmark | Codellama 70b Instruct | ERNIE 5.1 |
|---|---|---|
| LMArena Expert | — | 1492 |
Multilingual ERNIE 5.1 leads
Codellama 70b Instruct: 24.8 (#288), ERNIE 5.1: 55.5 (#29)
| Benchmark | Codellama 70b Instruct | ERNIE 5.1 |
|---|---|---|
| LMArena Non-English | 992 | 1454 |
| LMArena Chinese | — | 1508 |
| LMArena French | — | 1488 |
| LMArena German | — | 1470 |
| LMArena Japanese | — | 1422 |
| LMArena Korean | — | 1427 |
| LMArena Russian | — | 1459 |
| LMArena Spanish | — | 1473 |
Instruction Following ERNIE 5.1 leads
Codellama 70b Instruct: 51.9 (#293), ERNIE 5.1: 76.7 (#37)
| Benchmark | Codellama 70b Instruct | ERNIE 5.1 |
|---|---|---|
| LMArena Instruction Following | 1024 | 1460 |
Long Context Not comparable
Codellama 70b Instruct: —, ERNIE 5.1: 44.7 (#59)
| Benchmark | Codellama 70b Instruct | ERNIE 5.1 |
|---|---|---|
| LMArena Longer Query | — | 1462 |
Writing & Preference ERNIE 5.1 leads
Codellama 70b Instruct: 33.4 (#277), ERNIE 5.1: 65.1 (#52)
| Benchmark | Codellama 70b Instruct | ERNIE 5.1 |
|---|---|---|
| LMArena Text | 1057 | 1468 |
| LMArena Creative Writing | — | 1441 |
| LMArena Multi-Turn | — | 1471 |
Frequently asked questions
Is Codellama 70b Instruct better than ERNIE 5.1?
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 33.7 on the Noometry Index.
Is Codellama 70b Instruct or ERNIE 5.1 better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 37.6 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and ERNIE 5.1 share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and ERNIE 5.1 has 19.