Model comparison
DeepSeek LLM 67B vs Yi-1.5-34B
Yi-1.5-34B is the stronger model overall, scoring 30.2 to 24.8 on the Noometry Index.
Last verified . 12 shared benchmarks.
DeepSeekSummary
- They share 12 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Yi-1.5-34B in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Yi-1.5-34B leads 25.3 to 8.1.
- The biggest single-benchmark swing is MATH Level 5: 6.4% for DeepSeek LLM 67B and 25.5% for Yi-1.5-34B.
Side by side
| DeepSeek LLM 67B | Yi-1.5-34B | |
|---|---|---|
| Provider | DeepSeek | 01.AI |
| Noometry Index | 24.8 | 30.2 |
| Released | 2023-11-29 | 2024-05-13 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DeepSeek LLM 67B: 31.3 (#273), Yi-1.5-34B: 31.9 (#267)
| Benchmark | DeepSeek LLM 67B | Yi-1.5-34B |
|---|---|---|
| LMArena Coding | 1096 | 1169 |
| BigCodeBench Instruct | — | 33.9% |
| BigCodeBench Complete | — | 43.8% |
Reasoning Yi-1.5-34B leads
DeepSeek LLM 67B: 15.9 (#300), Yi-1.5-34B: 21.5 (#195)
| Benchmark | DeepSeek LLM 67B | Yi-1.5-34B |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1160 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.54 | — |
Math Yi-1.5-34B leads
DeepSeek LLM 67B: 8.1 (#318), Yi-1.5-34B: 25.3 (#248)
| Benchmark | DeepSeek LLM 67B | Yi-1.5-34B |
|---|---|---|
| LMArena Math | 1108 | 1182 |
| MATH Level 5 | 6.4% | 25.5% |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
Knowledge Yi-1.5-34B leads
DeepSeek LLM 67B: 7.1 (#308), Yi-1.5-34B: 14.8 (#290)
| Benchmark | DeepSeek LLM 67B | Yi-1.5-34B |
|---|---|---|
| GPQA Diamond | 24.6% | 32% |
| LMArena Expert | — | 1144 |
Multilingual Yi-1.5-34B leads
DeepSeek LLM 67B: 29.5 (#262), Yi-1.5-34B: 32.5 (#251)
| Benchmark | DeepSeek LLM 67B | Yi-1.5-34B |
|---|---|---|
| LMArena Non-English | 1073 | 1121 |
| LMArena Chinese | 1132 | 1213 |
| LMArena French | — | 1155 |
| LMArena German | — | 1111 |
| LMArena Japanese | — | 1021 |
| LMArena Korean | — | 1005 |
| LMArena Russian | — | 1091 |
| LMArena Spanish | — | 1120 |
Instruction Following Yi-1.5-34B leads
DeepSeek LLM 67B: 55.7 (#272), Yi-1.5-34B: 59.4 (#252)
| Benchmark | DeepSeek LLM 67B | Yi-1.5-34B |
|---|---|---|
| LMArena Instruction Following | 1079 | 1139 |
Long Context Yi-1.5-34B leads
DeepSeek LLM 67B: 33.1 (#260), Yi-1.5-34B: 34.6 (#243)
| Benchmark | DeepSeek LLM 67B | Yi-1.5-34B |
|---|---|---|
| LMArena Longer Query | 1092 | 1144 |
Writing & Preference Yi-1.5-34B leads
DeepSeek LLM 67B: 31.8 (#277), Yi-1.5-34B: 37.6 (#252)
| Benchmark | DeepSeek LLM 67B | Yi-1.5-34B |
|---|---|---|
| LMArena Text | 1105 | 1173 |
| LMArena Creative Writing | 1067 | 1135 |
| LMArena Multi-Turn | 1082 | 1153 |
Frequently asked questions
Is DeepSeek LLM 67B better than Yi-1.5-34B?
Yi-1.5-34B is the stronger model overall, scoring 30.2 to 24.8 on the Noometry Index.
Is DeepSeek LLM 67B or Yi-1.5-34B better for coding?
They score almost the same on coding (31.3 vs 31.9); test both on your own repository before choosing.
How many benchmarks do DeepSeek LLM 67B and Yi-1.5-34B share?
12 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Yi-1.5-34B has 21.