Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs Gemma 1.1 7b IT
Gemma 1.1 7b IT has enough public results to be ranked (#277); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
DeepSeek
GoogleSummary
- The widest gap is in coding, where DeepSeek-V2 (MoE-236B, May 2024) leads 40.4 to 31.5.
Side by side
| DeepSeek-V2 (MoE-236B, May 2024) | Gemma 1.1 7b IT | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 40.3 | 31.3 |
| Released | 2024-05-07 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 10 | 19 |
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 1.1 7b IT: 31.5 (#284)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 1.1 7b IT |
|---|---|---|
| BigCodeBench Instruct | 48.9% | — |
| LMArena Coding | — | 1084 |
| BigCodeBench Complete | 59.4% | — |
| HumanEval+ | — | 35.4% |
| MBPP+ | — | 45% |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Gemma 1.1 7b IT: 20.5 (#238)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 1.1 7b IT |
|---|---|---|
| LMArena Hard Prompts | — | 1071 |
| BIG-Bench Hard | 78.8% | — |
| Epoch Capabilities Index | 124.77 | — |
| HellaSwag | 87.1% | — |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |
Math Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Gemma 1.1 7b IT: 32.0 (#220)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 1.1 7b IT |
|---|---|---|
| LMArena Math | — | 1107 |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Gemma 1.1 7b IT: 28.3 (#247)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 1.1 7b IT |
|---|---|---|
| LMArena Expert | — | 1039 |
| ARC (AI2) Challenge | 92.2% | — |
| MMLU | 78.4% | — |
| TriviaQA | 80% | — |
Multilingual Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Gemma 1.1 7b IT: 28.1 (#273)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 1.1 7b IT |
|---|---|---|
| LMArena Non-English | — | 1052 |
| LMArena Chinese | — | 1061 |
| LMArena French | — | 1065 |
| LMArena German | — | 1054 |
| LMArena Japanese | — | 971 |
| LMArena Korean | — | 988 |
| LMArena Russian | — | 1046 |
| LMArena Spanish | — | 1049 |
Instruction Following Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Gemma 1.1 7b IT: 54.0 (#283)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 1.1 7b IT |
|---|---|---|
| LMArena Instruction Following | — | 1057 |
Long Context Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Gemma 1.1 7b IT: 32.1 (#272)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 1.1 7b IT |
|---|---|---|
| LMArena Longer Query | — | 1056 |
Writing & Preference Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Gemma 1.1 7b IT: 30.4 (#288)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 1.1 7b IT |
|---|---|---|
| LMArena Text | — | 1094 |
| LMArena Creative Writing | — | 1060 |
| LMArena Multi-Turn | — | 1040 |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than Gemma 1.1 7b IT?
Gemma 1.1 7b IT has enough public results to be ranked (#277); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is DeepSeek-V2 (MoE-236B, May 2024) or Gemma 1.1 7b IT better for coding?
DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 40.4 versus 31.5 in the Noometry coding category.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and Gemma 1.1 7b IT share?
0 benchmarks have published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and Gemma 1.1 7b IT has 19.