Model comparison
DeepSeek Coder 33B vs Gemma 3 4B
Gemma 3 4B has enough public results to be ranked (#326); DeepSeek Coder 33B 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 Coder 33B scores higher in 1 category and Gemma 3 4B in 0 categories; one gap is clear of the uncertainty.
Side by side
| DeepSeek Coder 33B | Gemma 3 4B | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 38.9 | 28.1 |
| Released | 2023-11-02 | 2025-03-12 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.04 |
| Output $ / M tokens | — | $0.08 |
| Results tracked | 9 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek Coder 33B leads
DeepSeek Coder 33B: 38.0 (#184), Gemma 3 4B: 35.9 (#215)
| Benchmark | DeepSeek Coder 33B | Gemma 3 4B |
|---|---|---|
| BigCodeBench Instruct | 42% | — |
| LMArena Coding | — | 1230 |
| BigCodeBench Complete | 51.1% | — |
| HumanEval+ | 75% | — |
| MBPP+ | 70.1% | — |
Agentic & Tool Use Not comparable
DeepSeek Coder 33B: —, Gemma 3 4B: 20.9 (#142)
| Benchmark | DeepSeek Coder 33B | Gemma 3 4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 19.6% |
Reasoning Not comparable
DeepSeek Coder 33B: —, Gemma 3 4B: 13.2 (#335)
| Benchmark | DeepSeek Coder 33B | Gemma 3 4B |
|---|---|---|
| Epoch Capabilities Index | 96.32 | 116.02 |
| Kagi LLM Benchmark | — | 25.2% |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | — | 1253 |
| DTBench | — | 50.9% |
| LMCA | — | 2.8% |
| WinoGrande | 62% | — |
Math Not comparable
DeepSeek Coder 33B: —, Gemma 3 4B: 16.8 (#292)
| Benchmark | DeepSeek Coder 33B | Gemma 3 4B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 7.5% |
| LMArena Math | — | 1239 |
| GSM8K | 35.4% | — |
Knowledge Not comparable
DeepSeek Coder 33B: —, Gemma 3 4B: 11.8 (#299)
| Benchmark | DeepSeek Coder 33B | Gemma 3 4B |
|---|---|---|
| GPQA Diamond | — | 23.2% |
| Vectara Hallucination Rate | — | 6.4% |
| LMArena Expert | — | 1223 |
| ARC (AI2) Challenge | 42.2% | — |
| MMLU | 39.4% | — |
Multilingual Not comparable
DeepSeek Coder 33B: —, Gemma 3 4B: 42.5 (#194)
| Benchmark | DeepSeek Coder 33B | Gemma 3 4B |
|---|---|---|
| LMArena Non-English | — | 1273 |
| LMArena German | — | 1281 |
| LMArena Russian | — | 1294 |
Instruction Following Not comparable
DeepSeek Coder 33B: —, Gemma 3 4B: 65.2 (#225)
| Benchmark | DeepSeek Coder 33B | Gemma 3 4B |
|---|---|---|
| LMArena Instruction Following | — | 1239 |
Long Context Not comparable
DeepSeek Coder 33B: —, Gemma 3 4B: 38.7 (#194)
| Benchmark | DeepSeek Coder 33B | Gemma 3 4B |
|---|---|---|
| LMArena Longer Query | — | 1273 |
Writing & Preference Not comparable
DeepSeek Coder 33B: —, Gemma 3 4B: 42.0 (#239)
| Benchmark | DeepSeek Coder 33B | Gemma 3 4B |
|---|---|---|
| LMArena Text | — | 1291 |
| LMArena Creative Writing | — | 1271 |
| EQ-Bench Creative Writing | — | 1068 |
| LMArena Multi-Turn | — | 1255 |
Frequently asked questions
Is DeepSeek Coder 33B better than Gemma 3 4B?
Gemma 3 4B has enough public results to be ranked (#326); DeepSeek Coder 33B does not yet, so treat this comparison as directional.
Is DeepSeek Coder 33B or Gemma 3 4B better for coding?
DeepSeek Coder 33B scores higher on coding benchmarks: 38.0 versus 35.9 in the Noometry coding category.
How many benchmarks do DeepSeek Coder 33B and Gemma 3 4B share?
1 benchmark has published results for both models. DeepSeek Coder 33B has 9 scored results on Noometry and Gemma 3 4B has 22.