Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs Gemma 3 4B
Gemma 3 4B has enough public results to be ranked (#320); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
DeepSeek
GoogleSummary
- They share 1 benchmark with published results for both. DeepSeek-V2 (MoE-236B, May 2024) scores higher in 1 category and Gemma 3 4B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-V2 (MoE-236B, May 2024) leads 39.8 to 35.3.
Side by side
| DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 4B | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 39.7 | 27.9 |
| Released | 2024-05-07 | 2025-03-12 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.04 |
| Output $ / M tokens | — | $0.08 |
| Results tracked | 10 | 22 |
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): 39.8 (#141), Gemma 3 4B: 35.3 (#214)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 4B |
|---|---|---|
| BigCodeBench Instruct | 48.9% | — |
| LMArena Coding | — | 1230 |
| BigCodeBench Complete | 59.4% | — |
Agentic & Tool Use Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Gemma 3 4B: 20.7 (#134)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 19.6% |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Gemma 3 4B: 12.7 (#330)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 4B |
|---|---|---|
| Epoch Capabilities Index | 124.78 | 116.02 |
| Kagi LLM Benchmark | — | 25.2% |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | — | 1253 |
| DTBench | — | 50.9% |
| LMCA | — | 2.8% |
| BIG-Bench Hard | 78.8% | — |
| HellaSwag | 87.1% | — |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |
Math Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Gemma 3 4B: 15.8 (#286)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 4B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 7.5% |
| LMArena Math | — | 1239 |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Gemma 3 4B: 11.8 (#294)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 4B |
|---|---|---|
| GPQA Diamond | — | 23.2% |
| Vectara Hallucination Rate | — | 6.4% |
| LMArena Expert | — | 1223 |
| ARC (AI2) Challenge | 92.2% | — |
| MMLU | 78.4% | — |
| TriviaQA | 80% | — |
Multilingual Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Gemma 3 4B: 42.7 (#189)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 4B |
|---|---|---|
| LMArena Non-English | — | 1273 |
| LMArena German | — | 1281 |
| LMArena Russian | — | 1294 |
Instruction Following Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Gemma 3 4B: 65.4 (#219)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 4B |
|---|---|---|
| LMArena Instruction Following | — | 1239 |
Long Context Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Gemma 3 4B: 38.6 (#189)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 4B |
|---|---|---|
| LMArena Longer Query | — | 1274 |
Writing & Preference Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Gemma 3 4B: 42.2 (#234)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 4B |
|---|---|---|
| LMArena Text | — | 1291 |
| LMArena Creative Writing | — | 1270 |
| EQ-Bench Creative Writing | — | 1068 |
| LMArena Multi-Turn | — | 1255 |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than Gemma 3 4B?
Gemma 3 4B has enough public results to be ranked (#320); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is DeepSeek-V2 (MoE-236B, May 2024) or Gemma 3 4B better for coding?
DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 39.8 versus 35.3 in the Noometry coding category.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and Gemma 3 4B share?
1 benchmark has published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and Gemma 3 4B has 22.