Model comparison
Command R vs ERNIE 5.1
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 31.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
Cohere
BaiduSummary
- They share 17 benchmarks with published results for both. Command R scores higher in 0 categories and ERNIE 5.1 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.1 to 38.2.
- Command R has downloadable open weights; the other is API-only.
Side by side
| Command R | ERNIE 5.1 | |
|---|---|---|
| Provider | Cohere | Baidu |
| Noometry Index | 31.4 | 43.8 |
| Released | 2024-08-30 | — |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 29 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding ERNIE 5.1 leads
Command R: 29.3 (#306), ERNIE 5.1: 44.0 (#76)
| Benchmark | Command R | ERNIE 5.1 |
|---|---|---|
| LMArena Coding | 1169 | 1488 |
| BigCodeBench Instruct | 37.1% | — |
| LiveBench Coding | 17.9% | — |
| BigCodeBench Complete | 45.2% | — |
Agentic & Tool Use Not comparable
Command R: —, ERNIE 5.1: —
| Benchmark | Command R | ERNIE 5.1 |
|---|---|---|
| LMArena Search | — | 1227 |
Reasoning ERNIE 5.1 leads
Command R: 13.8 (#331), ERNIE 5.1: 21.9 (#211)
| Benchmark | Command R | ERNIE 5.1 |
|---|---|---|
| LMArena Hard Prompts | 1164 | 1481 |
| NYT Connections (extended) | — | 23.4% |
| LiveBench Reasoning | 21.9% | — |
| DTBench | 46.4% | — |
| LiveBench Data Analysis | 33.3% | — |
| LMCA | 9.2% | — |
| LiveBench | 27.5% | — |
Math ERNIE 5.1 leads
Command R: 28.0 (#246), ERNIE 5.1: 40.3 (#92)
| Benchmark | Command R | ERNIE 5.1 |
|---|---|---|
| LMArena Math | 1155 | 1481 |
| LiveBench Math | 19.4% | — |
Knowledge ERNIE 5.1 leads
Command R: 31.0 (#221), ERNIE 5.1: 41.9 (#102)
| Benchmark | Command R | ERNIE 5.1 |
|---|---|---|
| LMArena Expert | 1138 | 1492 |
| MMLU | 65.2% | — |
Multilingual ERNIE 5.1 leads
Command R: 35.7 (#245), ERNIE 5.1: 55.5 (#29)
| Benchmark | Command R | ERNIE 5.1 |
|---|---|---|
| LMArena Non-English | 1174 | 1454 |
| LMArena Chinese | 1182 | 1508 |
| LMArena French | 1162 | 1488 |
| LMArena German | 1176 | 1470 |
| LMArena Japanese | 1143 | 1422 |
| LMArena Korean | 1163 | 1427 |
| LMArena Russian | 1174 | 1459 |
| LMArena Spanish | 1151 | 1473 |
Instruction Following ERNIE 5.1 leads
Command R: 58.1 (#261), ERNIE 5.1: 76.7 (#37)
| Benchmark | Command R | ERNIE 5.1 |
|---|---|---|
| LMArena Instruction Following | 1167 | 1460 |
| LiveBench Instruction Following | 55.6% | — |
Long Context ERNIE 5.1 leads
Command R: 36.3 (#231), ERNIE 5.1: 44.7 (#59)
| Benchmark | Command R | ERNIE 5.1 |
|---|---|---|
| LMArena Longer Query | 1198 | 1462 |
Writing & Preference ERNIE 5.1 leads
Command R: 38.2 (#254), ERNIE 5.1: 65.1 (#52)
| Benchmark | Command R | ERNIE 5.1 |
|---|---|---|
| LMArena Text | 1187 | 1468 |
| LMArena Creative Writing | 1170 | 1441 |
| LMArena Multi-Turn | 1163 | 1471 |
| LiveBench Language | 16.7% | — |
Frequently asked questions
Is Command R better than ERNIE 5.1?
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 31.4 on the Noometry Index.
Is Command R or ERNIE 5.1 better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 29.3 in the Noometry coding category.
How many benchmarks do Command R and ERNIE 5.1 share?
17 benchmarks have published results for both models. Command R has 29 scored results on Noometry and ERNIE 5.1 has 19.