Model comparison
DeepSeek LLM 67B vs Yi-Lightning
Yi-Lightning is the stronger model overall, scoring 37.1 to 24.9 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeekSummary
- They share 10 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 1 category and Yi-Lightning in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Yi-Lightning leads 35.4 to 7.0.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | Yi-Lightning | |
|---|---|---|
| Provider | DeepSeek | 01.AI |
| Noometry Index | 24.9 | 37.1 |
| Released | 2023-11-29 | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek LLM 67B leads
DeepSeek LLM 67B: 31.9 (#278), Yi-Lightning: 27.4 (#320)
| Benchmark | DeepSeek LLM 67B | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1096 | 1312 |
| Aider Polyglot | — | 12.9% |
Reasoning Yi-Lightning leads
DeepSeek LLM 67B: 16.5 (#304), Yi-Lightning: 25.9 (#139)
| Benchmark | DeepSeek LLM 67B | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1302 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.5 | — |
Math Yi-Lightning leads
DeepSeek LLM 67B: 8.7 (#324), Yi-Lightning: 36.2 (#172)
| Benchmark | DeepSeek LLM 67B | Yi-Lightning |
|---|---|---|
| LMArena Math | 1108 | 1300 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |
Knowledge Yi-Lightning leads
DeepSeek LLM 67B: 7.0 (#313), Yi-Lightning: 35.4 (#185)
| Benchmark | DeepSeek LLM 67B | Yi-Lightning |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| LMArena Expert | — | 1286 |
Multilingual Yi-Lightning leads
DeepSeek LLM 67B: 29.4 (#267), Yi-Lightning: 42.2 (#196)
| Benchmark | DeepSeek LLM 67B | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1073 | 1269 |
| LMArena Chinese | 1132 | 1320 |
| LMArena French | — | 1305 |
| LMArena German | — | 1267 |
| LMArena Japanese | — | 1228 |
| LMArena Korean | — | 1192 |
| LMArena Russian | — | 1255 |
| LMArena Spanish | — | 1315 |
Instruction Following Yi-Lightning leads
DeepSeek LLM 67B: 55.4 (#277), Yi-Lightning: 67.4 (#196)
| Benchmark | DeepSeek LLM 67B | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1079 | 1278 |
Long Context Yi-Lightning leads
DeepSeek LLM 67B: 33.1 (#265), Yi-Lightning: 39.4 (#181)
| Benchmark | DeepSeek LLM 67B | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1092 | 1297 |
Writing & Preference Yi-Lightning leads
DeepSeek LLM 67B: 31.6 (#282), Yi-Lightning: 50.2 (#184)
| Benchmark | DeepSeek LLM 67B | Yi-Lightning |
|---|---|---|
| LMArena Text | 1105 | 1302 |
| LMArena Creative Writing | 1067 | 1280 |
| LMArena Multi-Turn | 1082 | 1311 |
Frequently asked questions
Is DeepSeek LLM 67B better than Yi-Lightning?
Yi-Lightning is the stronger model overall, scoring 37.1 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Yi-Lightning better for coding?
DeepSeek LLM 67B scores higher on coding benchmarks: 31.9 versus 27.4 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Yi-Lightning share?
10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Yi-Lightning has 18.