Model comparison
DeepSeek LLM 67B vs Yi-34B
Yi-34B is the stronger model overall, scoring 27.8 to 24.9 on the Noometry Index.
Last verified . 13 shared benchmarks.
DeepSeekSummary
- They share 13 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Yi-34B in 8 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Yi-34B leads 21.6 to 8.7.
- The biggest single-benchmark swing is GPQA Diamond: 24.6% for DeepSeek LLM 67B and 14.7% for Yi-34B.
Side by side
| DeepSeek LLM 67B | Yi-34B | |
|---|---|---|
| Provider | DeepSeek | 01.AI |
| Noometry Index | 24.9 | 27.8 |
| Released | 2023-11-29 | 2023-11-02 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DeepSeek LLM 67B: 31.9 (#278), Yi-34B: 32.3 (#274)
| Benchmark | DeepSeek LLM 67B | Yi-34B |
|---|---|---|
| LMArena Coding | 1096 | 1112 |
Reasoning Yi-34B leads
DeepSeek LLM 67B: 16.5 (#304), Yi-34B: 21.2 (#226)
| Benchmark | DeepSeek LLM 67B | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1104 |
| Epoch Capabilities Index | 110.5 | 117.39 |
| Chess Puzzles | 0% | — |
| BIG-Bench Hard | — | 71.7% |
Math Yi-34B leads
DeepSeek LLM 67B: 8.7 (#324), Yi-34B: 21.6 (#282)
| Benchmark | DeepSeek LLM 67B | Yi-34B |
|---|---|---|
| LMArena Math | 1108 | 1114 |
| MATH Level 5 | 6.4% | 5.1% |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| GSM8K | — | 76% |
Knowledge Too close to call
DeepSeek LLM 67B: 7.0 (#313), Yi-34B: 7.5 (#309)
| Benchmark | DeepSeek LLM 67B | Yi-34B |
|---|---|---|
| GPQA Diamond | 24.6% | 14.7% |
| LMArena Expert | — | 1061 |
| MMLU | — | 76.3% |
Multilingual Too close to call
DeepSeek LLM 67B: 29.4 (#267), Yi-34B: 29.7 (#264)
| Benchmark | DeepSeek LLM 67B | Yi-34B |
|---|---|---|
| LMArena Non-English | 1073 | 1079 |
| LMArena Chinese | 1132 | 1176 |
| LMArena French | — | 1081 |
| LMArena German | — | 1042 |
| LMArena Japanese | — | 993 |
| LMArena Korean | — | 959 |
| LMArena Russian | — | 1050 |
| LMArena Spanish | — | 1070 |
Instruction Following Too close to call
DeepSeek LLM 67B: 55.4 (#277), Yi-34B: 56.2 (#274)
| Benchmark | DeepSeek LLM 67B | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1079 | 1091 |
Long Context Too close to call
DeepSeek LLM 67B: 33.1 (#265), Yi-34B: 33.2 (#264)
| Benchmark | DeepSeek LLM 67B | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1092 | 1094 |
Writing & Preference Yi-34B leads
DeepSeek LLM 67B: 31.6 (#282), Yi-34B: 34.1 (#273)
| Benchmark | DeepSeek LLM 67B | Yi-34B |
|---|---|---|
| LMArena Text | 1105 | 1129 |
| LMArena Creative Writing | 1067 | 1108 |
| LMArena Multi-Turn | 1082 | 1113 |
Frequently asked questions
Is DeepSeek LLM 67B better than Yi-34B?
Yi-34B is the stronger model overall, scoring 27.8 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Yi-34B better for coding?
They score almost the same on coding (31.9 vs 32.3); test both on your own repository before choosing.
How many benchmarks do DeepSeek LLM 67B and Yi-34B share?
13 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Yi-34B has 23.