Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs Gemma 2 27B
Gemma 2 27B has enough public results to be ranked (#312); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 4 shared benchmarks.
DeepSeek
GoogleSummary
- They share 4 benchmarks with published results for both. DeepSeek-V2 (MoE-236B, May 2024) scores higher in 1 category and Gemma 2 27B 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 34.1.
- The biggest single-benchmark swing is BigCodeBench Complete: 59.4% for DeepSeek-V2 (MoE-236B, May 2024) and 52.5% for Gemma 2 27B.
Side by side
| DeepSeek-V2 (MoE-236B, May 2024) | Gemma 2 27B | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 40.3 | 29.4 |
| Released | 2024-05-07 | 2024-06-24 |
| Weights | Open | Open |
| Context window | — | 8K |
| Max output | — | 2K |
| Input $ / M tokens | — | $0.65 |
| Output $ / M tokens | — | $0.65 |
| Results tracked | 10 | 34 |
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), Gemma 2 27B: 34.1 (#246)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 2 27B |
|---|---|---|
| BigCodeBench Instruct | 48.9% | 42.8% |
| BigCodeBench Complete | 59.4% | 52.5% |
| LiveBench Coding | — | 36% |
| LMArena Coding | — | 1211 |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Gemma 2 27B: 15.3 (#315)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 2 27B |
|---|---|---|
| Epoch Capabilities Index | 124.77 | 122.08 |
| LiveBench Reasoning | — | 28.1% |
| LMArena Hard Prompts | — | 1198 |
| DTBench | — | 48% |
| LiveBench Data Analysis | — | 47.9% |
| LMCA | — | 7.1% |
| BIG-Bench Hard | 78.8% | — |
| HellaSwag | 87.1% | — |
| LiveBench | — | 38.2% |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |
Math Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Gemma 2 27B: 10.7 (#311)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 2 27B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 1.4% |
| LiveBench Math | — | 26.5% |
| LMArena Math | — | 1212 |
| MATH Level 5 | — | 27.9% |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Gemma 2 27B: 19.0 (#280)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 2 27B |
|---|---|---|
| MMLU | 78.4% | 75.7% |
| GPQA Diamond | — | 36.5% |
| Confabulations | — | 27.1% |
| LMArena Expert | — | 1172 |
| ARC (AI2) Challenge | 92.2% | — |
| TriviaQA | 80% | — |
Multilingual Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Gemma 2 27B: 38.6 (#226)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 2 27B |
|---|---|---|
| LMArena Non-English | — | 1217 |
| LMArena Chinese | — | 1221 |
| LMArena French | — | 1247 |
| LMArena German | — | 1209 |
| LMArena Japanese | — | 1175 |
| LMArena Korean | — | 1174 |
| LMArena Russian | — | 1234 |
| LMArena Spanish | — | 1228 |
Instruction Following Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Gemma 2 27B: 60.5 (#249)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 2 27B |
|---|---|---|
| LiveBench Instruction Following | — | 58.1% |
| LMArena Instruction Following | — | 1206 |
Long Context Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Gemma 2 27B: 37.3 (#218)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 2 27B |
|---|---|---|
| LMArena Longer Query | — | 1231 |
Writing & Preference Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Gemma 2 27B: 44.2 (#225)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 2 27B |
|---|---|---|
| LMArena Text | — | 1231 |
| LMArena Creative Writing | — | 1241 |
| LMArena Multi-Turn | — | 1224 |
| LiveBench Language | — | 32.6% |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than Gemma 2 27B?
Gemma 2 27B has enough public results to be ranked (#312); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is DeepSeek-V2 (MoE-236B, May 2024) or Gemma 2 27B better for coding?
DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 40.4 versus 34.1 in the Noometry coding category.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and Gemma 2 27B share?
4 benchmarks have published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and Gemma 2 27B has 34.