Model comparison
DeepSeek-V3.1 vs ERNIE 5.1
DeepSeek-V3.1 and ERNIE 5.1 score almost the same on the Noometry Index (42.2 vs 43.1), so choose on price, context window or the category you care about most.
Last verified . 17 shared benchmarks.
DeepSeek
BaiduSummary
- They share 17 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 2 categories and ERNIE 5.1 in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where ERNIE 5.1 leads 44.7 to 36.3.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1 | ERNIE 5.1 | |
|---|---|---|
| Provider | DeepSeek | Baidu |
| Noometry Index | 42.2 | 43.1 |
| Released | 2025-08-21 | — |
| Weights | Open | Proprietary |
| Context window | 164K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.95 | — |
| Results tracked | 27 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding ERNIE 5.1 leads
DeepSeek-V3.1: 39.8 (#140), ERNIE 5.1: 43.4 (#78)
| Benchmark | DeepSeek-V3.1 | ERNIE 5.1 |
|---|---|---|
| LMArena Coding | 1417 | 1488 |
| WeirdML | 38.4% | — |
Agentic & Tool Use Not comparable
DeepSeek-V3.1: —, ERNIE 5.1: —
| Benchmark | DeepSeek-V3.1 | ERNIE 5.1 |
|---|---|---|
| LMArena Search | — | 1227 |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.3 (#109), ERNIE 5.1: 20.9 (#209)
| Benchmark | DeepSeek-V3.1 | ERNIE 5.1 |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1481 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| NYT Connections (extended) | — | 23.4% |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| Epoch Capabilities Index | 139.92 | — |
| ForecastBench | 58 | — |
Math ERNIE 5.1 leads
DeepSeek-V3.1: 36.1 (#125), ERNIE 5.1: 37.5 (#96)
| Benchmark | DeepSeek-V3.1 | ERNIE 5.1 |
|---|---|---|
| LMArena Math | 1420 | 1481 |
Knowledge DeepSeek-V3.1 leads
DeepSeek-V3.1: 43.0 (#86), ERNIE 5.1: 41.2 (#103)
| Benchmark | DeepSeek-V3.1 | ERNIE 5.1 |
|---|---|---|
| LMArena Expert | 1403 | 1491 |
| Vectara Hallucination Rate | 5.5% | — |
Multilingual ERNIE 5.1 leads
DeepSeek-V3.1: 51.8 (#100), ERNIE 5.1: 55.7 (#28)
| Benchmark | DeepSeek-V3.1 | ERNIE 5.1 |
|---|---|---|
| LMArena Non-English | 1400 | 1455 |
| LMArena Chinese | 1470 | 1507 |
| LMArena French | 1447 | 1486 |
| LMArena German | 1412 | 1470 |
| LMArena Japanese | 1374 | 1422 |
| LMArena Korean | 1337 | 1428 |
| LMArena Russian | 1405 | 1459 |
| LMArena Spanish | 1429 | 1472 |
Instruction Following ERNIE 5.1 leads
DeepSeek-V3.1: 74.1 (#105), ERNIE 5.1: 76.9 (#35)
| Benchmark | DeepSeek-V3.1 | ERNIE 5.1 |
|---|---|---|
| LMArena Instruction Following | 1400 | 1460 |
Long Context ERNIE 5.1 leads
DeepSeek-V3.1: 36.3 (#227), ERNIE 5.1: 44.7 (#56)
| Benchmark | DeepSeek-V3.1 | ERNIE 5.1 |
|---|---|---|
| LMArena Longer Query | 1422 | 1462 |
| Fiction.LiveBench | 52.8% | — |
Writing & Preference ERNIE 5.1 leads
DeepSeek-V3.1: 60.5 (#93), ERNIE 5.1: 65.3 (#50)
| Benchmark | DeepSeek-V3.1 | ERNIE 5.1 |
|---|---|---|
| LMArena Text | 1420 | 1468 |
| LMArena Creative Writing | 1401 | 1440 |
| LMArena Multi-Turn | 1408 | 1471 |
| EQ-Bench Creative Writing | 1436 | — |
Frequently asked questions
Is DeepSeek-V3.1 better than ERNIE 5.1?
DeepSeek-V3.1 and ERNIE 5.1 score almost the same on the Noometry Index (42.2 vs 43.1), so choose on price, context window or the category you care about most.
Is DeepSeek-V3.1 or ERNIE 5.1 better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 43.4 versus 39.8 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1 and ERNIE 5.1 share?
17 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and ERNIE 5.1 has 19.