Model comparison
DeepSeek-V3.1-Terminus vs Gemma 2 27B
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 29.4 on the Noometry Index.
Last verified . 12 shared benchmarks.
DeepSeek
GoogleSummary
- They share 12 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 7 categories and Gemma 2 27B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-V3.1-Terminus leads 38.5 to 10.7.
- The biggest single-benchmark swing is DTBench: 81.3% for DeepSeek-V3.1-Terminus and 48% for Gemma 2 27B.
- DeepSeek-V3.1-Terminus is cheaper at $0.27 / $1 per million input/output tokens, against $0.65 / $0.65 for Gemma 2 27B.
- DeepSeek-V3.1-Terminus accepts more context: 164K tokens versus 8K.
Side by side
| DeepSeek-V3.1-Terminus | Gemma 2 27B | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 43.1 | 29.4 |
| Released | 2025-09-22 | 2024-06-24 |
| Weights | Open | Open |
| Context window | 164K | 8K |
| Max output | 147K | 2K |
| Input $ / M tokens | $0.27 | $0.65 |
| Output $ / M tokens | $1 | $0.65 |
| Results tracked | 16 | 34 |
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: 42.0 (#113), Gemma 2 27B: 34.1 (#246)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2 27B |
|---|---|---|
| LMArena Coding | 1426 | 1211 |
| SciCode | 40.6% | — |
| BigCodeBench Instruct | — | 42.8% |
| LiveBench Coding | — | 36% |
| BigCodeBench Complete | — | 52.5% |
| ALE-Bench | 745.17 | — |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 26.4 (#133), Gemma 2 27B: 15.3 (#315)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2 27B |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1198 |
| DTBench | 81.3% | 48% |
| LMCA | 28.6% | 7.1% |
| Kagi LLM Benchmark | 57.4% | — |
| CritPt | 1.7% | — |
| LiveBench Reasoning | — | 28.1% |
| LiveBench Data Analysis | — | 47.9% |
| Epoch Capabilities Index | — | 122.08 |
| LiveBench | — | 38.2% |
Math DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 38.5 (#137), Gemma 2 27B: 10.7 (#311)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2 27B |
|---|---|---|
| LMArena Math | 1402 | 1212 |
| OTIS Mock AIME 2024-2025 | — | 1.4% |
| LiveBench Math | — | 26.5% |
| MATH Level 5 | — | 27.9% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Gemma 2 27B: 19.0 (#280)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2 27B |
|---|---|---|
| GPQA Diamond | — | 36.5% |
| Confabulations | — | 27.1% |
| LMArena Expert | — | 1172 |
| MMLU | — | 75.7% |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.1 (#92), Gemma 2 27B: 38.6 (#226)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2 27B |
|---|---|---|
| LMArena Non-English | 1407 | 1217 |
| LMArena Russian | 1436 | 1234 |
| LMArena Chinese | — | 1221 |
| LMArena French | — | 1247 |
| LMArena German | — | 1209 |
| LMArena Japanese | — | 1175 |
| LMArena Korean | — | 1174 |
| LMArena Spanish | — | 1228 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.0 (#106), Gemma 2 27B: 60.5 (#249)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2 27B |
|---|---|---|
| LMArena Instruction Following | 1404 | 1206 |
| LiveBench Instruction Following | — | 58.1% |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.4 (#97), Gemma 2 27B: 37.3 (#218)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2 27B |
|---|---|---|
| LMArena Longer Query | 1421 | 1231 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.0 (#92), Gemma 2 27B: 44.2 (#225)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2 27B |
|---|---|---|
| LMArena Text | 1419 | 1231 |
| LMArena Creative Writing | 1403 | 1241 |
| LMArena Multi-Turn | 1411 | 1224 |
| LiveBench Language | — | 32.6% |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Gemma 2 27B?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 29.4 on the Noometry Index.
Which is cheaper, DeepSeek-V3.1-Terminus or Gemma 2 27B?
DeepSeek-V3.1-Terminus is cheaper. It lists at $0.27 per million input tokens and $1 per million output tokens; Gemma 2 27B lists at $0.65 and $0.65.
Is DeepSeek-V3.1-Terminus or Gemma 2 27B better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
DeepSeek-V3.1-Terminus does, with 164K tokens against 8K.
How many benchmarks do DeepSeek-V3.1-Terminus and Gemma 2 27B share?
12 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Gemma 2 27B has 34.