Model comparison
DeepSeek LLM 67B vs Gemma 3 27B
Gemma 3 27B is the stronger model overall, scoring 30.8 to 24.9 on the Noometry Index.
Last verified . 15 shared benchmarks.
DeepSeek
GoogleSummary
- They share 15 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 2 categories and Gemma 3 27B in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 3 27B leads 52.5 to 31.6.
- The biggest single-benchmark swing is MATH Level 5: 6.4% for DeepSeek LLM 67B and 74% for Gemma 3 27B.
Side by side
| DeepSeek LLM 67B | Gemma 3 27B | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 24.9 | 30.8 |
| Released | 2023-11-29 | 2025-03-11 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.08 |
| Output $ / M tokens | — | $0.16 |
| Results tracked | 15 | 43 |
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 3 27B: 22.5 (#334)
| Benchmark | DeepSeek LLM 67B | Gemma 3 27B |
|---|---|---|
| LMArena Coding | 1096 | 1322 |
| Aider Polyglot | — | 4.9% |
| SciCode | — | 21.2% |
| LiveBench Coding | — | 39.9% |
Agentic & Tool Use Not comparable
DeepSeek LLM 67B: —, Gemma 3 27B: 25.1 (#110)
| Benchmark | DeepSeek LLM 67B | Gemma 3 27B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 29.5% |
Reasoning Too close to call
DeepSeek LLM 67B: 16.5 (#304), Gemma 3 27B: 16.7 (#301)
| Benchmark | DeepSeek LLM 67B | Gemma 3 27B |
|---|---|---|
| Chess Puzzles | 0% | 0% |
| LMArena Hard Prompts | 1070 | 1340 |
| Epoch Capabilities Index | 110.5 | 130.04 |
| Kagi LLM Benchmark | — | 40.4% |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 43.8% |
| DTBench | — | 52.5% |
| LiveBench Data Analysis | — | 51.5% |
| LMCA | — | 12.3% |
| LiveBench | — | 50% |
Math Gemma 3 27B leads
DeepSeek LLM 67B: 8.7 (#324), Gemma 3 27B: 25.9 (#265)
| Benchmark | DeepSeek LLM 67B | Gemma 3 27B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 22.5% |
| LMArena Math | 1108 | 1312 |
| MATH Level 5 | 6.4% | 74% |
| LiveBench Math | — | 55.4% |
Knowledge Gemma 3 27B leads
DeepSeek LLM 67B: 7.0 (#313), Gemma 3 27B: 25.5 (#261)
| Benchmark | DeepSeek LLM 67B | Gemma 3 27B |
|---|---|---|
| GPQA Diamond | 24.6% | 47.7% |
| Confabulations | — | 40.3% |
| Vectara Hallucination Rate | — | 7.4% |
| LMArena Expert | — | 1304 |
Multimodal Not comparable
DeepSeek LLM 67B: —, Gemma 3 27B: 32.6 (#100)
| Benchmark | DeepSeek LLM 67B | Gemma 3 27B |
|---|---|---|
| LMArena Vision | — | 1164 |
| GeoBench | — | 52% |
Multilingual Gemma 3 27B leads
DeepSeek LLM 67B: 29.4 (#267), Gemma 3 27B: 46.9 (#155)
| Benchmark | DeepSeek LLM 67B | Gemma 3 27B |
|---|---|---|
| LMArena Non-English | 1073 | 1334 |
| LMArena Chinese | 1132 | 1346 |
| LMArena French | — | 1368 |
| LMArena German | — | 1362 |
| LMArena Japanese | — | 1287 |
| LMArena Korean | — | 1308 |
| LMArena Russian | — | 1349 |
| LMArena Spanish | — | 1349 |
Instruction Following Gemma 3 27B leads
DeepSeek LLM 67B: 55.4 (#277), Gemma 3 27B: 70.6 (#160)
| Benchmark | DeepSeek LLM 67B | Gemma 3 27B |
|---|---|---|
| LMArena Instruction Following | 1079 | 1321 |
| LiveBench Instruction Following | — | 74.9% |
Long Context DeepSeek LLM 67B leads
DeepSeek LLM 67B: 33.1 (#265), Gemma 3 27B: 27.6 (#293)
| Benchmark | DeepSeek LLM 67B | Gemma 3 27B |
|---|---|---|
| LMArena Longer Query | 1092 | 1333 |
| Fiction.LiveBench | — | 33.3% |
Writing & Preference Gemma 3 27B leads
DeepSeek LLM 67B: 31.6 (#282), Gemma 3 27B: 52.5 (#168)
| Benchmark | DeepSeek LLM 67B | Gemma 3 27B |
|---|---|---|
| LMArena Text | 1105 | 1358 |
| LMArena Creative Writing | 1067 | 1346 |
| LMArena Multi-Turn | 1082 | 1345 |
| Short-Story Creative Writing | — | 79.9% |
| EQ-Bench Creative Writing | — | 1266 |
| LiveBench Language | — | 34.6% |
Frequently asked questions
Is DeepSeek LLM 67B better than Gemma 3 27B?
Gemma 3 27B is the stronger model overall, scoring 30.8 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Gemma 3 27B better for coding?
DeepSeek LLM 67B scores higher on coding benchmarks: 31.9 versus 22.5 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Gemma 3 27B share?
15 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Gemma 3 27B has 43.