# DeepSeek-V3.1-Terminus vs Gemma 7B

> DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 30.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v3-1-terminus-vs-gemma-7b
- Last updated: 2026-10-10
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 7 categories and Gemma 7B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.0 to 27.1.

## Snapshot

| | DeepSeek-V3.1-Terminus | Gemma 7B |
|---|---|---|
| Provider | DeepSeek | Google |
| Noometry Index | 43.1 | 30.0 |
| Rank | 97 | 299 |
| Context | 164K | — |
| Input $/M | $0.27 | — |
| Output $/M | $1 | — |
| Weights | Open | Open |

## Coding

- DeepSeek-V3.1-Terminus: 42.0 (#113)
- Gemma 7B: 30.5 (#294)

| Benchmark | DeepSeek-V3.1-Terminus | Gemma 7B |
|---|---|---|
| LMArena Coding | 1426 | 1048 |
| SciCode | 40.6% | — |
| ALE-Bench | 745.17 | — |
| HumanEval+ | — | 28.7% |
| MBPP+ | — | 43.4% |

## Reasoning

- DeepSeek-V3.1-Terminus: 26.4 (#133)
- Gemma 7B: 19.9 (#249)

| Benchmark | DeepSeek-V3.1-Terminus | Gemma 7B |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1042 |
| Kagi LLM Benchmark | 57.4% | — |
| CritPt | 1.7% | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |
| Adversarial NLI | — | 48.7% |
| BIG-Bench Hard | — | 55.1% |
| Epoch Capabilities Index | — | 111.99 |
| HellaSwag | — | 82.2% |
| PIQA | — | 81.2% |
| WinoGrande | — | 79% |

## Math

- DeepSeek-V3.1-Terminus: 38.5 (#137)
- Gemma 7B: 31.2 (#228)

| Benchmark | DeepSeek-V3.1-Terminus | Gemma 7B |
|---|---|---|
| LMArena Math | 1402 | 1066 |
| GSM8K | — | 46.4% |

## Knowledge

- DeepSeek-V3.1-Terminus: —
- Gemma 7B: 27.3 (#252)

| Benchmark | DeepSeek-V3.1-Terminus | Gemma 7B |
|---|---|---|
| LMArena Expert | — | 1001 |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 83.2% |
| MMLU | — | 66.1% |
| OpenBookQA | — | 78.6% |
| TriviaQA | — | 72.3% |

## Multilingual

- DeepSeek-V3.1-Terminus: 52.1 (#92)
- Gemma 7B: 25.1 (#287)

| Benchmark | DeepSeek-V3.1-Terminus | Gemma 7B |
|---|---|---|
| LMArena Non-English | 1407 | 999 |
| LMArena Russian | 1436 | 993 |
| LMArena Chinese | — | 1035 |
| LMArena French | — | 1025 |

## Instruction Following

- DeepSeek-V3.1-Terminus: 74.0 (#106)
- Gemma 7B: 51.5 (#295)

| Benchmark | DeepSeek-V3.1-Terminus | Gemma 7B |
|---|---|---|
| LMArena Instruction Following | 1404 | 1017 |

## Long Context

- DeepSeek-V3.1-Terminus: 43.4 (#97)
- Gemma 7B: 31.1 (#282)

| Benchmark | DeepSeek-V3.1-Terminus | Gemma 7B |
|---|---|---|
| LMArena Longer Query | 1421 | 1022 |

## Writing & Preference

- DeepSeek-V3.1-Terminus: 61.0 (#92)
- Gemma 7B: 27.1 (#302)

| Benchmark | DeepSeek-V3.1-Terminus | Gemma 7B |
|---|---|---|
| LMArena Text | 1419 | 1056 |
| LMArena Creative Writing | 1403 | 1024 |
| LMArena Multi-Turn | 1411 | 963 |

## FAQ

### Is DeepSeek-V3.1-Terminus better than Gemma 7B?

DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 30.0 on the Noometry Index.

### Is DeepSeek-V3.1-Terminus or Gemma 7B better for coding?

DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 30.5 in the Noometry coding category.

### How many benchmarks do DeepSeek-V3.1-Terminus and Gemma 7B share?

10 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Gemma 7B has 27.