Model comparison
DeepSeek-V3.2-Speciale vs ERNIE 5.1
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 39.7 on the Noometry Index.
Last verified . 0 shared benchmarks.
DeepSeek
BaiduSummary
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.1 to 46.0.
- DeepSeek-V3.2-Speciale has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.2-Speciale | ERNIE 5.1 | |
|---|---|---|
| Provider | DeepSeek | Baidu |
| Noometry Index | 39.7 | 43.8 |
| Released | 2025-12-01 | — |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.58 | — |
| Output $ / M tokens | $1.68 | — |
| Results tracked | 3 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding ERNIE 5.1 leads
DeepSeek-V3.2-Speciale: 40.4 (#140), ERNIE 5.1: 44.0 (#76)
| Benchmark | DeepSeek-V3.2-Speciale | ERNIE 5.1 |
|---|---|---|
| WeirdML | 46.7% | — |
| LMArena Coding | — | 1488 |
Agentic & Tool Use Not comparable
DeepSeek-V3.2-Speciale: —, ERNIE 5.1: —
| Benchmark | DeepSeek-V3.2-Speciale | ERNIE 5.1 |
|---|---|---|
| LMArena Search | — | 1227 |
Reasoning DeepSeek-V3.2-Speciale leads
DeepSeek-V3.2-Speciale: 32.9 (#73), ERNIE 5.1: 21.9 (#211)
| Benchmark | DeepSeek-V3.2-Speciale | ERNIE 5.1 |
|---|---|---|
| SimpleBench | 52.6% | — |
| NYT Connections (extended) | — | 23.4% |
| LMArena Hard Prompts | — | 1481 |
Math Not comparable
DeepSeek-V3.2-Speciale: —, ERNIE 5.1: 40.3 (#92)
| Benchmark | DeepSeek-V3.2-Speciale | ERNIE 5.1 |
|---|---|---|
| LMArena Math | — | 1481 |
Knowledge Not comparable
DeepSeek-V3.2-Speciale: —, ERNIE 5.1: 41.9 (#102)
| Benchmark | DeepSeek-V3.2-Speciale | ERNIE 5.1 |
|---|---|---|
| LMArena Expert | — | 1492 |
Multilingual Not comparable
DeepSeek-V3.2-Speciale: —, ERNIE 5.1: 55.5 (#29)
| Benchmark | DeepSeek-V3.2-Speciale | ERNIE 5.1 |
|---|---|---|
| LMArena Non-English | — | 1454 |
| LMArena Chinese | — | 1508 |
| LMArena French | — | 1488 |
| LMArena German | — | 1470 |
| LMArena Japanese | — | 1422 |
| LMArena Korean | — | 1427 |
| LMArena Russian | — | 1459 |
| LMArena Spanish | — | 1473 |
Instruction Following Not comparable
DeepSeek-V3.2-Speciale: —, ERNIE 5.1: 76.7 (#37)
| Benchmark | DeepSeek-V3.2-Speciale | ERNIE 5.1 |
|---|---|---|
| LMArena Instruction Following | — | 1460 |
Long Context Not comparable
DeepSeek-V3.2-Speciale: —, ERNIE 5.1: 44.7 (#59)
| Benchmark | DeepSeek-V3.2-Speciale | ERNIE 5.1 |
|---|---|---|
| LMArena Longer Query | — | 1462 |
Writing & Preference ERNIE 5.1 leads
DeepSeek-V3.2-Speciale: 46.0 (#222), ERNIE 5.1: 65.1 (#52)
| Benchmark | DeepSeek-V3.2-Speciale | ERNIE 5.1 |
|---|---|---|
| LMArena Text | — | 1468 |
| LMArena Creative Writing | — | 1441 |
| EQ-Bench Creative Writing | 1276 | — |
| LMArena Multi-Turn | — | 1471 |
Frequently asked questions
Is DeepSeek-V3.2-Speciale better than ERNIE 5.1?
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 39.7 on the Noometry Index.
Is DeepSeek-V3.2-Speciale or ERNIE 5.1 better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 40.4 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.2-Speciale and ERNIE 5.1 share?
0 benchmarks have published results for both models. DeepSeek-V3.2-Speciale has 3 scored results on Noometry and ERNIE 5.1 has 19.