Model comparison
DeepSeek-V2.5 (Sep 2024) vs ERNIE 5.1
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 37.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeek
BaiduSummary
- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 1 category and ERNIE 5.1 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.1 to 49.8.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2.5 (Sep 2024) | ERNIE 5.1 | |
|---|---|---|
| Provider | DeepSeek | Baidu |
| Noometry Index | 37.6 | 43.8 |
| Released | 2024-09-06 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding ERNIE 5.1 leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), ERNIE 5.1: 44.0 (#76)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | ERNIE 5.1 |
|---|---|---|
| LMArena Coding | 1309 | 1488 |
| Aider Polyglot | 17.8% | — |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Agentic & Tool Use Not comparable
DeepSeek-V2.5 (Sep 2024): —, ERNIE 5.1: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | ERNIE 5.1 |
|---|---|---|
| LMArena Search | — | 1227 |
Reasoning DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), ERNIE 5.1: 21.9 (#211)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | ERNIE 5.1 |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1481 |
| NYT Connections (extended) | — | 23.4% |
Math ERNIE 5.1 leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), ERNIE 5.1: 40.3 (#92)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | ERNIE 5.1 |
|---|---|---|
| LMArena Math | 1288 | 1481 |
Knowledge ERNIE 5.1 leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), ERNIE 5.1: 41.9 (#102)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | ERNIE 5.1 |
|---|---|---|
| LMArena Expert | 1266 | 1492 |
Multilingual ERNIE 5.1 leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), ERNIE 5.1: 55.5 (#29)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | ERNIE 5.1 |
|---|---|---|
| LMArena Non-English | 1273 | 1454 |
| LMArena Chinese | 1318 | 1508 |
| LMArena French | 1289 | 1488 |
| LMArena German | 1258 | 1470 |
| LMArena Japanese | 1228 | 1422 |
| LMArena Korean | 1209 | 1427 |
| LMArena Russian | 1289 | 1459 |
| LMArena Spanish | 1248 | 1473 |
Instruction Following ERNIE 5.1 leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), ERNIE 5.1: 76.7 (#37)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | ERNIE 5.1 |
|---|---|---|
| LMArena Instruction Following | 1280 | 1460 |
Long Context ERNIE 5.1 leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), ERNIE 5.1: 44.7 (#59)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | ERNIE 5.1 |
|---|---|---|
| LMArena Longer Query | 1301 | 1462 |
Writing & Preference ERNIE 5.1 leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), ERNIE 5.1: 65.1 (#52)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | ERNIE 5.1 |
|---|---|---|
| LMArena Text | 1294 | 1468 |
| LMArena Creative Writing | 1285 | 1441 |
| LMArena Multi-Turn | 1297 | 1471 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than ERNIE 5.1?
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or ERNIE 5.1 better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and ERNIE 5.1 share?
17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and ERNIE 5.1 has 19.