Model comparison
DeepSeek LLM 67B vs Gemma 7B
Gemma 7B is the stronger model overall, scoring 30.0 to 24.9 on the Noometry Index.
Last verified . 11 shared benchmarks.
DeepSeek
GoogleSummary
- They share 11 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 5 categories and Gemma 7B in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 7B leads 31.2 to 8.7.
Side by side
| DeepSeek LLM 67B | Gemma 7B | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 24.9 | 30.0 |
| Released | 2023-11-29 | 2024-02-21 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek LLM 67B leads
DeepSeek LLM 67B: 31.9 (#278), Gemma 7B: 30.5 (#294)
| Benchmark | DeepSeek LLM 67B | Gemma 7B |
|---|---|---|
| LMArena Coding | 1096 | 1048 |
| HumanEval+ | — | 28.7% |
| MBPP+ | — | 43.4% |
Reasoning Gemma 7B leads
DeepSeek LLM 67B: 16.5 (#304), Gemma 7B: 19.9 (#249)
| Benchmark | DeepSeek LLM 67B | Gemma 7B |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1042 |
| Epoch Capabilities Index | 110.5 | 111.99 |
| Chess Puzzles | 0% | — |
| Adversarial NLI | — | 48.7% |
| BIG-Bench Hard | — | 55.1% |
| HellaSwag | — | 82.2% |
| PIQA | — | 81.2% |
| WinoGrande | — | 79% |
Math Gemma 7B leads
DeepSeek LLM 67B: 8.7 (#324), Gemma 7B: 31.2 (#228)
| Benchmark | DeepSeek LLM 67B | Gemma 7B |
|---|---|---|
| LMArena Math | 1108 | 1066 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |
| GSM8K | — | 46.4% |
Knowledge Gemma 7B leads
DeepSeek LLM 67B: 7.0 (#313), Gemma 7B: 27.3 (#252)
| Benchmark | DeepSeek LLM 67B | Gemma 7B |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| LMArena Expert | — | 1001 |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 83.2% |
| MMLU | — | 66.1% |
| OpenBookQA | — | 78.6% |
| TriviaQA | — | 72.3% |
Multilingual DeepSeek LLM 67B leads
DeepSeek LLM 67B: 29.4 (#267), Gemma 7B: 25.1 (#287)
| Benchmark | DeepSeek LLM 67B | Gemma 7B |
|---|---|---|
| LMArena Non-English | 1073 | 999 |
| LMArena Chinese | 1132 | 1035 |
| LMArena French | — | 1025 |
| LMArena Russian | — | 993 |
Instruction Following DeepSeek LLM 67B leads
DeepSeek LLM 67B: 55.4 (#277), Gemma 7B: 51.5 (#295)
| Benchmark | DeepSeek LLM 67B | Gemma 7B |
|---|---|---|
| LMArena Instruction Following | 1079 | 1017 |
Long Context DeepSeek LLM 67B leads
DeepSeek LLM 67B: 33.1 (#265), Gemma 7B: 31.1 (#282)
| Benchmark | DeepSeek LLM 67B | Gemma 7B |
|---|---|---|
| LMArena Longer Query | 1092 | 1022 |
Writing & Preference DeepSeek LLM 67B leads
DeepSeek LLM 67B: 31.6 (#282), Gemma 7B: 27.1 (#302)
| Benchmark | DeepSeek LLM 67B | Gemma 7B |
|---|---|---|
| LMArena Text | 1105 | 1056 |
| LMArena Creative Writing | 1067 | 1024 |
| LMArena Multi-Turn | 1082 | 963 |
Frequently asked questions
Is DeepSeek LLM 67B better than Gemma 7B?
Gemma 7B is the stronger model overall, scoring 30.0 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Gemma 7B better for coding?
DeepSeek LLM 67B scores higher on coding benchmarks: 31.9 versus 30.5 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Gemma 7B share?
11 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Gemma 7B has 27.