Model comparison
DeepSeek-V3.1 vs Gemma 7B
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 30.0 on the Noometry Index.
Last verified . 14 shared benchmarks.
DeepSeek
GoogleSummary
- They share 14 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 8 categories and Gemma 7B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1 leads 60.3 to 27.1.
Side by side
| DeepSeek-V3.1 | Gemma 7B | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 42.8 | 30.0 |
| Released | 2025-08-21 | 2024-02-21 |
| Weights | Open | Open |
| Context window | 164K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.95 | — |
| Results tracked | 27 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1 leads
DeepSeek-V3.1: 40.3 (#144), Gemma 7B: 30.5 (#294)
| Benchmark | DeepSeek-V3.1 | Gemma 7B |
|---|---|---|
| LMArena Coding | 1417 | 1048 |
| WeirdML | 38.4% | — |
| HumanEval+ | — | 28.7% |
| MBPP+ | — | 43.4% |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.9 (#110), Gemma 7B: 19.9 (#249)
| Benchmark | DeepSeek-V3.1 | Gemma 7B |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1042 |
| Epoch Capabilities Index | 139.92 | 111.99 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| Adversarial NLI | — | 48.7% |
| BIG-Bench Hard | — | 55.1% |
| ForecastBench | 58 | — |
| HellaSwag | — | 82.2% |
| PIQA | — | 81.2% |
| WinoGrande | — | 79% |
Math DeepSeek-V3.1 leads
DeepSeek-V3.1: 38.9 (#122), Gemma 7B: 31.2 (#228)
| Benchmark | DeepSeek-V3.1 | Gemma 7B |
|---|---|---|
| LMArena Math | 1420 | 1066 |
| GSM8K | — | 46.4% |
Knowledge DeepSeek-V3.1 leads
DeepSeek-V3.1: 43.7 (#90), Gemma 7B: 27.3 (#252)
| Benchmark | DeepSeek-V3.1 | Gemma 7B |
|---|---|---|
| LMArena Expert | 1405 | 1001 |
| Vectara Hallucination Rate | 5.5% | — |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 83.2% |
| MMLU | — | 66.1% |
| OpenBookQA | — | 78.6% |
| TriviaQA | — | 72.3% |
Multilingual DeepSeek-V3.1 leads
DeepSeek-V3.1: 51.6 (#106), Gemma 7B: 25.1 (#287)
| Benchmark | DeepSeek-V3.1 | Gemma 7B |
|---|---|---|
| LMArena Non-English | 1400 | 999 |
| LMArena Chinese | 1469 | 1035 |
| LMArena French | 1447 | 1025 |
| LMArena Russian | 1405 | 993 |
| LMArena German | 1411 | — |
| LMArena Japanese | 1378 | — |
| LMArena Korean | 1337 | — |
| LMArena Spanish | 1431 | — |
Instruction Following DeepSeek-V3.1 leads
DeepSeek-V3.1: 73.9 (#110), Gemma 7B: 51.5 (#295)
| Benchmark | DeepSeek-V3.1 | Gemma 7B |
|---|---|---|
| LMArena Instruction Following | 1400 | 1017 |
Long Context DeepSeek-V3.1 leads
DeepSeek-V3.1: 36.3 (#232), Gemma 7B: 31.1 (#282)
| Benchmark | DeepSeek-V3.1 | Gemma 7B |
|---|---|---|
| LMArena Longer Query | 1422 | 1022 |
| Fiction.LiveBench | 52.8% | — |
Writing & Preference DeepSeek-V3.1 leads
DeepSeek-V3.1: 60.3 (#98), Gemma 7B: 27.1 (#302)
| Benchmark | DeepSeek-V3.1 | Gemma 7B |
|---|---|---|
| LMArena Text | 1420 | 1056 |
| LMArena Creative Writing | 1401 | 1024 |
| LMArena Multi-Turn | 1408 | 963 |
| EQ-Bench Creative Writing | 1436 | — |
Frequently asked questions
Is DeepSeek-V3.1 better than Gemma 7B?
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 30.0 on the Noometry Index.
Is DeepSeek-V3.1 or Gemma 7B better for coding?
DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 30.5 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1 and Gemma 7B share?
14 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Gemma 7B has 27.