Model comparison
DeepSeek-V3.1-Terminus vs ERNIE 5.0 0110
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 41.8 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeek
BaiduSummary
- They share 10 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 1 category and ERNIE 5.0 0110 in 6 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek-V3.1-Terminus leads 26.4 to 17.0.
- DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1-Terminus | ERNIE 5.0 0110 | |
|---|---|---|
| Provider | DeepSeek | Baidu |
| Noometry Index | 43.1 | 41.8 |
| Released | 2025-09-22 | — |
| Weights | Open | Proprietary |
| Context window | 164K | — |
| Max output | 147K | — |
| Input $ / M tokens | $0.27 | — |
| Output $ / M tokens | $1 | — |
| Results tracked | 16 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DeepSeek-V3.1-Terminus: 42.0 (#113), ERNIE 5.0 0110: 43.0 (#94)
| Benchmark | DeepSeek-V3.1-Terminus | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Coding | 1426 | 1455 |
| SciCode | 40.6% | — |
| ALE-Bench | 745.17 | — |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 26.4 (#133), ERNIE 5.0 0110: 17.0 (#297)
| Benchmark | DeepSeek-V3.1-Terminus | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1445 |
| Kagi LLM Benchmark | 57.4% | — |
| NYT Connections (extended) | — | 10.3% |
| CritPt | 1.7% | — |
| Thematic Generalization | — | 41.7% |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |
Math Too close to call
DeepSeek-V3.1-Terminus: 38.5 (#137), ERNIE 5.0 0110: 39.3 (#110)
| Benchmark | DeepSeek-V3.1-Terminus | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Math | 1402 | 1437 |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, ERNIE 5.0 0110: 39.8 (#128)
| Benchmark | DeepSeek-V3.1-Terminus | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Expert | — | 1428 |
Multimodal Not comparable
DeepSeek-V3.1-Terminus: —, ERNIE 5.0 0110: 39.9 (#53)
| Benchmark | DeepSeek-V3.1-Terminus | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Vision | — | 1249 |
Multilingual ERNIE 5.0 0110 leads
DeepSeek-V3.1-Terminus: 52.1 (#92), ERNIE 5.0 0110: 54.1 (#49)
| Benchmark | DeepSeek-V3.1-Terminus | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Non-English | 1407 | 1436 |
| LMArena Russian | 1436 | 1446 |
| LMArena Chinese | — | 1512 |
| LMArena French | — | 1467 |
| LMArena German | — | 1460 |
| LMArena Japanese | — | 1382 |
| LMArena Korean | — | 1406 |
| LMArena Spanish | — | 1473 |
Instruction Following Too close to call
DeepSeek-V3.1-Terminus: 74.0 (#106), ERNIE 5.0 0110: 74.5 (#92)
| Benchmark | DeepSeek-V3.1-Terminus | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Instruction Following | 1404 | 1413 |
Long Context Too close to call
DeepSeek-V3.1-Terminus: 43.4 (#97), ERNIE 5.0 0110: 43.4 (#95)
| Benchmark | DeepSeek-V3.1-Terminus | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Longer Query | 1421 | 1422 |
Writing & Preference ERNIE 5.0 0110 leads
DeepSeek-V3.1-Terminus: 61.0 (#92), ERNIE 5.0 0110: 63.1 (#66)
| Benchmark | DeepSeek-V3.1-Terminus | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Text | 1419 | 1445 |
| LMArena Creative Writing | 1403 | 1426 |
| LMArena Multi-Turn | 1411 | 1434 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than ERNIE 5.0 0110?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 41.8 on the Noometry Index.
Is DeepSeek-V3.1-Terminus or ERNIE 5.0 0110 better for coding?
They score almost the same on coding (42.0 vs 43.0); test both on your own repository before choosing.
How many benchmarks do DeepSeek-V3.1-Terminus and ERNIE 5.0 0110 share?
10 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and ERNIE 5.0 0110 has 20.