Model comparison
DeepSeek LLM 67B vs DeepSeek-V2 (MoE-236B, May 2024)
DeepSeek LLM 67B has enough public results to be ranked (#341); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
DeepSeekSummary
- They share 1 benchmark with published results for both. DeepSeek LLM 67B scores higher in 0 categories and DeepSeek-V2 (MoE-236B, May 2024) in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-V2 (MoE-236B, May 2024) leads 39.8 to 31.3.
Side by side
| DeepSeek LLM 67B | DeepSeek-V2 (MoE-236B, May 2024) | |
|---|---|---|
| Provider | DeepSeek | DeepSeek |
| Noometry Index | 24.8 | 39.7 |
| Released | 2023-11-29 | 2024-05-07 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V2 (MoE-236B, May 2024) leads
DeepSeek LLM 67B: 31.3 (#273), DeepSeek-V2 (MoE-236B, May 2024): 39.8 (#141)
| Benchmark | DeepSeek LLM 67B | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| BigCodeBench Instruct | — | 48.9% |
| LMArena Coding | 1096 | — |
| BigCodeBench Complete | — | 59.4% |
Reasoning Not comparable
DeepSeek LLM 67B: 15.9 (#300), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | DeepSeek LLM 67B | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| Epoch Capabilities Index | 110.54 | 124.78 |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1070 | — |
| BIG-Bench Hard | — | 78.8% |
| HellaSwag | — | 87.1% |
| PIQA | — | 83.9% |
| WinoGrande | — | 86.3% |
Math Not comparable
DeepSeek LLM 67B: 8.1 (#318), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | DeepSeek LLM 67B | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| LMArena Math | 1108 | — |
| MATH Level 5 | 6.4% | — |
Knowledge Not comparable
DeepSeek LLM 67B: 7.1 (#308), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | DeepSeek LLM 67B | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| ARC (AI2) Challenge | — | 92.2% |
| MMLU | — | 78.4% |
| TriviaQA | — | 80% |
Multilingual Not comparable
DeepSeek LLM 67B: 29.5 (#262), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | DeepSeek LLM 67B | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Non-English | 1073 | — |
| LMArena Chinese | 1132 | — |
Instruction Following Not comparable
DeepSeek LLM 67B: 55.7 (#272), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | DeepSeek LLM 67B | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Instruction Following | 1079 | — |
Long Context Not comparable
DeepSeek LLM 67B: 33.1 (#260), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | DeepSeek LLM 67B | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Longer Query | 1092 | — |
Writing & Preference Not comparable
DeepSeek LLM 67B: 31.8 (#277), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | DeepSeek LLM 67B | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Text | 1105 | — |
| LMArena Creative Writing | 1067 | — |
| LMArena Multi-Turn | 1082 | — |
Frequently asked questions
Is DeepSeek LLM 67B better than DeepSeek-V2 (MoE-236B, May 2024)?
DeepSeek LLM 67B has enough public results to be ranked (#341); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is DeepSeek LLM 67B or DeepSeek-V2 (MoE-236B, May 2024) better for coding?
DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 39.8 versus 31.3 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and DeepSeek-V2 (MoE-236B, May 2024) share?
1 benchmark has published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and DeepSeek-V2 (MoE-236B, May 2024) has 10.