Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs Yi-34B
Yi-34B has enough public results to be ranked (#329); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 3 shared benchmarks.
DeepSeekSummary
- They share 3 benchmarks with published results for both. DeepSeek-V2 (MoE-236B, May 2024) scores higher in 1 category and Yi-34B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-V2 (MoE-236B, May 2024) leads 40.4 to 32.3.
Side by side
| DeepSeek-V2 (MoE-236B, May 2024) | Yi-34B | |
|---|---|---|
| Provider | DeepSeek | 01.AI |
| Noometry Index | 40.3 | 27.8 |
| Released | 2024-05-07 | 2023-11-02 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 10 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V2 (MoE-236B, May 2024) leads
DeepSeek-V2 (MoE-236B, May 2024): 40.4 (#139), Yi-34B: 32.3 (#274)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Yi-34B |
|---|---|---|
| BigCodeBench Instruct | 48.9% | — |
| LMArena Coding | — | 1112 |
| BigCodeBench Complete | 59.4% | — |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Yi-34B: 21.2 (#226)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Yi-34B |
|---|---|---|
| BIG-Bench Hard | 78.8% | 71.7% |
| Epoch Capabilities Index | 124.77 | 117.39 |
| LMArena Hard Prompts | — | 1104 |
| HellaSwag | 87.1% | — |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |
Math Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Yi-34B: 21.6 (#282)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Yi-34B |
|---|---|---|
| LMArena Math | — | 1114 |
| MATH Level 5 | — | 5.1% |
| GSM8K | — | 76% |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Yi-34B: 7.5 (#309)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Yi-34B |
|---|---|---|
| MMLU | 78.4% | 76.3% |
| GPQA Diamond | — | 14.7% |
| LMArena Expert | — | 1061 |
| ARC (AI2) Challenge | 92.2% | — |
| TriviaQA | 80% | — |
Multilingual Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Yi-34B: 29.7 (#264)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Yi-34B |
|---|---|---|
| LMArena Non-English | — | 1079 |
| LMArena Chinese | — | 1176 |
| LMArena French | — | 1081 |
| LMArena German | — | 1042 |
| LMArena Japanese | — | 993 |
| LMArena Korean | — | 959 |
| LMArena Russian | — | 1050 |
| LMArena Spanish | — | 1070 |
Instruction Following Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Yi-34B: 56.2 (#274)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Yi-34B |
|---|---|---|
| LMArena Instruction Following | — | 1091 |
Long Context Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Yi-34B: 33.2 (#264)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Yi-34B |
|---|---|---|
| LMArena Longer Query | — | 1094 |
Writing & Preference Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Yi-34B: 34.1 (#273)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Yi-34B |
|---|---|---|
| LMArena Text | — | 1129 |
| LMArena Creative Writing | — | 1108 |
| LMArena Multi-Turn | — | 1113 |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than Yi-34B?
Yi-34B has enough public results to be ranked (#329); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is DeepSeek-V2 (MoE-236B, May 2024) or Yi-34B better for coding?
DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 40.4 versus 32.3 in the Noometry coding category.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and Yi-34B share?
3 benchmarks have published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and Yi-34B has 23.