# DeepSeek-V3.1-Terminus vs Gemma 2 9B

> DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 25.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v3-1-terminus-vs-gemma-2-9b
- 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 2 9B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.3 to 32.3.

## Snapshot

| | DeepSeek-V3.1-Terminus | Gemma 2 9B |
|---|---|---|
| Provider | DeepSeek | Google |
| Noometry Index | 42.6 | 25.7 |
| Rank | 96 | 334 |
| Context | 164K | — |
| Input $/M | $0.30 | — |
| Output $/M | $1 | — |
| Weights | Open | Open |

## Coding

- DeepSeek-V3.1-Terminus: 41.5 (#114)
- Gemma 2 9B: 29.0 (#299)

| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2 9B |
|---|---|---|
| LMArena Coding | 1426 | 1174 |
| SciCode | 40.6% | — |
| BigCodeBench Instruct | — | 34.7% |
| LiveBench Coding | — | 22.5% |
| BigCodeBench Complete | — | 40.6% |
| ALE-Bench | 745.17 | — |

## Reasoning

- DeepSeek-V3.1-Terminus: 25.7 (#126)
- Gemma 2 9B: 15.3 (#306)

| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2 9B |
|---|---|---|
| LMArena Hard Prompts | 1427 | 1172 |
| Kagi LLM Benchmark | 57.4% | — |
| CritPt | 1.7% | — |
| LiveBench Reasoning | — | 15.2% |
| DTBench | 81.3% | — |
| LiveBench Data Analysis | — | 36.4% |
| LMCA | 28.6% | — |
| Epoch Capabilities Index | — | 119.78 |
| LiveBench | — | 28.7% |
| PIQA | — | 83.7% |

## Math

- DeepSeek-V3.1-Terminus: 35.7 (#138)
- Gemma 2 9B: 9.3 (#312)

| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2 9B |
|---|---|---|
| LMArena Math | 1402 | 1183 |
| OTIS Mock AIME 2024-2025 | — | 0.6% |
| LiveBench Math | — | 19.8% |
| MATH Level 5 | — | 21% |
| GSM8K | — | 84.9% |

## Knowledge

- DeepSeek-V3.1-Terminus: —
- Gemma 2 9B: 9.7 (#300)

| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2 9B |
|---|---|---|
| GPQA Diamond | — | 27.5% |
| LMArena Expert | — | 1147 |
| BoolQ | — | 85.7% |
| MMLU | — | 72.1% |

## Multilingual

- DeepSeek-V3.1-Terminus: 52.3 (#87)
- Gemma 2 9B: 36.8 (#233)

| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2 9B |
|---|---|---|
| LMArena Non-English | 1407 | 1188 |
| LMArena Russian | 1434 | 1200 |
| LMArena Chinese | — | 1185 |
| LMArena French | — | 1189 |
| LMArena German | — | 1186 |
| LMArena Japanese | — | 1144 |
| LMArena Korean | — | 1137 |
| LMArena Spanish | — | 1200 |

## Instruction Following

- DeepSeek-V3.1-Terminus: 74.4 (#96)
- Gemma 2 9B: 57.8 (#264)

| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2 9B |
|---|---|---|
| LMArena Instruction Following | 1406 | 1178 |
| LiveBench Instruction Following | — | 52.6% |

## Long Context

- DeepSeek-V3.1-Terminus: 43.5 (#88)
- Gemma 2 9B: 36.3 (#228)

| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2 9B |
|---|---|---|
| LMArena Longer Query | 1426 | 1197 |

## Writing & Preference

- DeepSeek-V3.1-Terminus: 61.3 (#87)
- Gemma 2 9B: 32.3 (#276)

| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2 9B |
|---|---|---|
| LMArena Text | 1420 | 1207 |
| LMArena Creative Writing | 1404 | 1206 |
| LMArena Multi-Turn | 1411 | 1193 |
| EQ-Bench Creative Writing | — | 841 |
| LiveBench Language | — | 25.5% |

## FAQ

### Is DeepSeek-V3.1-Terminus better than Gemma 2 9B?

DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 25.7 on the Noometry Index.

### Is DeepSeek-V3.1-Terminus or Gemma 2 9B better for coding?

DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 29.0 in the Noometry coding category.

### How many benchmarks do DeepSeek-V3.1-Terminus and Gemma 2 9B share?

10 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Gemma 2 9B has 35.