Model comparison
DeepSeek-V3.1-Terminus vs Yi-Lightning
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 37.1 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeekSummary
- They share 10 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 7 categories and Yi-Lightning in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-V3.1-Terminus leads 42.0 to 27.4.
- DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1-Terminus | Yi-Lightning | |
|---|---|---|
| Provider | DeepSeek | 01.AI |
| Noometry Index | 43.1 | 37.1 |
| Released | 2025-09-22 | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | 164K | — |
| Max output | 147K | — |
| Input $ / M tokens | $0.27 | — |
| Output $ / M tokens | $1 | — |
| Results tracked | 16 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 42.0 (#113), Yi-Lightning: 27.4 (#320)
| Benchmark | DeepSeek-V3.1-Terminus | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1426 | 1312 |
| Aider Polyglot | — | 12.9% |
| SciCode | 40.6% | — |
| ALE-Bench | 745.17 | — |
Reasoning Too close to call
DeepSeek-V3.1-Terminus: 26.4 (#133), Yi-Lightning: 25.9 (#139)
| Benchmark | DeepSeek-V3.1-Terminus | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1302 |
| Kagi LLM Benchmark | 57.4% | — |
| CritPt | 1.7% | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |
Math DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 38.5 (#137), Yi-Lightning: 36.2 (#172)
| Benchmark | DeepSeek-V3.1-Terminus | Yi-Lightning |
|---|---|---|
| LMArena Math | 1402 | 1300 |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Yi-Lightning: 35.4 (#185)
| Benchmark | DeepSeek-V3.1-Terminus | Yi-Lightning |
|---|---|---|
| LMArena Expert | — | 1286 |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.1 (#92), Yi-Lightning: 42.2 (#196)
| Benchmark | DeepSeek-V3.1-Terminus | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1407 | 1269 |
| LMArena Russian | 1436 | 1255 |
| LMArena Chinese | — | 1320 |
| LMArena French | — | 1305 |
| LMArena German | — | 1267 |
| LMArena Japanese | — | 1228 |
| LMArena Korean | — | 1192 |
| LMArena Spanish | — | 1315 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.0 (#106), Yi-Lightning: 67.4 (#196)
| Benchmark | DeepSeek-V3.1-Terminus | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1404 | 1278 |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.4 (#97), Yi-Lightning: 39.4 (#181)
| Benchmark | DeepSeek-V3.1-Terminus | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1421 | 1297 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.0 (#92), Yi-Lightning: 50.2 (#184)
| Benchmark | DeepSeek-V3.1-Terminus | Yi-Lightning |
|---|---|---|
| LMArena Text | 1419 | 1302 |
| LMArena Creative Writing | 1403 | 1280 |
| LMArena Multi-Turn | 1411 | 1311 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Yi-Lightning?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 37.1 on the Noometry Index.
Is DeepSeek-V3.1-Terminus or Yi-Lightning better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 27.4 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1-Terminus and Yi-Lightning share?
10 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Yi-Lightning has 18.