Model comparison
DeepSeek-V3.1-Terminus vs Gemma 3 27B
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 30.5 on the Noometry Index. Gemma 3 27B costs 4.7× less per token, which makes it the better buy when DeepSeek-V3.1-Terminus's lead doesn't matter for your workload.
Last verified . 15 shared benchmarks.
DeepSeek
GoogleSummary
- They share 15 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 7 categories and Gemma 3 27B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-V3.1-Terminus leads 41.5 to 22.1.
- The biggest single-benchmark swing is DTBench: 81.3% for DeepSeek-V3.1-Terminus and 52.5% for Gemma 3 27B.
- Gemma 3 27B is cheaper at $0.08 / $0.16 per million input/output tokens, against $0.30 / $1 for DeepSeek-V3.1-Terminus.
- DeepSeek-V3.1-Terminus accepts more context: 164K tokens versus 131K.
Side by side
| DeepSeek-V3.1-Terminus | Gemma 3 27B | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 42.6 | 30.5 |
| Released | 2025-09-22 | 2025-03-11 |
| Weights | Open | Open |
| Context window | 164K | 131K |
| Max output | 66K | 8K |
| Input $ / M tokens | $0.30 | $0.08 |
| Output $ / M tokens | $1 | $0.16 |
| Results tracked | 16 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 41.5 (#114), Gemma 3 27B: 22.1 (#329)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 3 27B |
|---|---|---|
| SciCode | 40.6% | 21.2% |
| LMArena Coding | 1426 | 1322 |
| Aider Polyglot | — | 4.9% |
| LiveBench Coding | — | 39.9% |
| ALE-Bench | 745.17 | — |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, Gemma 3 27B: 24.9 (#105)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 3 27B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 29.5% |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 25.7 (#126), Gemma 3 27B: 16.3 (#297)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 3 27B |
|---|---|---|
| Kagi LLM Benchmark | 57.4% | 40.4% |
| CritPt | 1.7% | 0% |
| LMArena Hard Prompts | 1427 | 1340 |
| DTBench | 81.3% | 52.5% |
| LMCA | 28.6% | 12.3% |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 43.8% |
| LiveBench Data Analysis | — | 51.5% |
| Epoch Capabilities Index | — | 130.04 |
| LiveBench | — | 50% |
Math DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 35.7 (#138), Gemma 3 27B: 24.4 (#261)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 3 27B |
|---|---|---|
| LMArena Math | 1402 | 1312 |
| OTIS Mock AIME 2024-2025 | — | 22.5% |
| LiveBench Math | — | 55.4% |
| MATH Level 5 | — | 74% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Gemma 3 27B: 25.4 (#256)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 3 27B |
|---|---|---|
| GPQA Diamond | — | 47.7% |
| Confabulations | — | 40.3% |
| Vectara Hallucination Rate | — | 7.4% |
| LMArena Expert | — | 1303 |
Multimodal Not comparable
DeepSeek-V3.1-Terminus: —, Gemma 3 27B: 32.0 (#94)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 3 27B |
|---|---|---|
| LMArena Vision | — | 1165 |
| GeoBench | — | 52% |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.3 (#87), Gemma 3 27B: 47.0 (#150)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 3 27B |
|---|---|---|
| LMArena Non-English | 1407 | 1334 |
| LMArena Russian | 1434 | 1349 |
| LMArena Chinese | — | 1347 |
| LMArena French | — | 1368 |
| LMArena German | — | 1362 |
| LMArena Japanese | — | 1287 |
| LMArena Korean | — | 1308 |
| LMArena Spanish | — | 1348 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.4 (#96), Gemma 3 27B: 70.8 (#155)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 3 27B |
|---|---|---|
| LMArena Instruction Following | 1406 | 1321 |
| LiveBench Instruction Following | — | 74.9% |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.5 (#88), Gemma 3 27B: 27.6 (#288)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 3 27B |
|---|---|---|
| LMArena Longer Query | 1426 | 1333 |
| Fiction.LiveBench | — | 33.3% |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.3 (#87), Gemma 3 27B: 52.7 (#161)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 3 27B |
|---|---|---|
| LMArena Text | 1420 | 1358 |
| LMArena Creative Writing | 1404 | 1346 |
| LMArena Multi-Turn | 1411 | 1344 |
| Short-Story Creative Writing | — | 79.9% |
| EQ-Bench Creative Writing | — | 1266 |
| LiveBench Language | — | 34.6% |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Gemma 3 27B?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 30.5 on the Noometry Index. Gemma 3 27B costs 4.7× less per token, which makes it the better buy when DeepSeek-V3.1-Terminus's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-V3.1-Terminus or Gemma 3 27B?
Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; DeepSeek-V3.1-Terminus lists at $0.30 and $1.
Is DeepSeek-V3.1-Terminus or Gemma 3 27B better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 22.1 in the Noometry coding category.
Which has the bigger context window?
DeepSeek-V3.1-Terminus does, with 164K tokens against 131K.
How many benchmarks do DeepSeek-V3.1-Terminus and Gemma 3 27B share?
15 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Gemma 3 27B has 43.