Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs Gemma 1.1 2b IT
Gemma 1.1 2b IT has enough public results to be ranked (#313); 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 30.1.
Side by side
| DeepSeek-V2 (MoE-236B, May 2024) | Gemma 1.1 2b IT | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 40.3 | 29.3 |
| Released | 2024-05-07 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 10 | 16 |
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 2b IT: 30.1 (#299)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 1.1 2b IT |
|---|---|---|
| BigCodeBench Instruct | 48.9% | — |
| LMArena Coding | — | 1034 |
| BigCodeBench Complete | 59.4% | — |
| HumanEval+ | — | 17.7% |
| MBPP+ | — | 23.3% |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Gemma 1.1 2b IT: 19.1 (#270)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 1.1 2b IT |
|---|---|---|
| LMArena Hard Prompts | — | 1005 |
| 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 2b IT: 30.8 (#232)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 1.1 2b IT |
|---|---|---|
| LMArena Math | — | 1047 |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Gemma 1.1 2b IT: 26.5 (#258)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 1.1 2b IT |
|---|---|---|
| LMArena Expert | — | 970 |
| ARC (AI2) Challenge | 92.2% | — |
| MMLU | 78.4% | — |
| TriviaQA | 80% | — |
Multilingual Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Gemma 1.1 2b IT: 24.6 (#289)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 1.1 2b IT |
|---|---|---|
| LMArena Non-English | — | 988 |
| LMArena Chinese | — | 1012 |
| LMArena German | — | 944 |
| LMArena Korean | — | 899 |
| LMArena Russian | — | 990 |
Instruction Following Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Gemma 1.1 2b IT: 49.9 (#299)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 1.1 2b IT |
|---|---|---|
| LMArena Instruction Following | — | 992 |
Long Context Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Gemma 1.1 2b IT: 30.6 (#286)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 1.1 2b IT |
|---|---|---|
| LMArena Longer Query | — | 1003 |
Writing & Preference Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Gemma 1.1 2b IT: 25.1 (#306)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 1.1 2b IT |
|---|---|---|
| LMArena Text | — | 1022 |
| LMArena Creative Writing | — | 998 |
| LMArena Multi-Turn | — | 959 |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than Gemma 1.1 2b IT?
Gemma 1.1 2b IT has enough public results to be ranked (#313); 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 2b IT better for coding?
DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 40.4 versus 30.1 in the Noometry coding category.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and Gemma 1.1 2b 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 2b IT has 16.