# DeepSeek-V3.1 vs Gemini 1.5 Flash 8B

> DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 29.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v3-1-vs-gemini-1-5-flash-8b
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 7 categories and Gemini 1.5 Flash 8B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-V3.1 leads 43.0 to 16.0.
- The biggest single-benchmark swing is DTBench: 82.7% for DeepSeek-V3.1 and 50% for Gemini 1.5 Flash 8B.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek-V3.1 | Gemini 1.5 Flash 8B |
|---|---|---|
| Provider | DeepSeek | Google |
| Noometry Index | 42.2 | 29.7 |
| Rank | 106 | 292 |
| Context | 164K | — |
| Input $/M | $0.25 | — |
| Output $/M | $0.95 | — |
| Weights | Open | Proprietary |

## Coding

- DeepSeek-V3.1: 39.8 (#140)
- Gemini 1.5 Flash 8B: 34.9 (#221)

| Benchmark | DeepSeek-V3.1 | Gemini 1.5 Flash 8B |
|---|---|---|
| LMArena Coding | 1417 | 1218 |
| WeirdML | 38.4% | — |

## Reasoning

- DeepSeek-V3.1: 27.3 (#109)
- Gemini 1.5 Flash 8B: 19.2 (#242)

| Benchmark | DeepSeek-V3.1 | Gemini 1.5 Flash 8B |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1210 |
| DTBench | 82.7% | 50% |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| LMCA | 24.3% | — |
| Epoch Capabilities Index | 139.92 | — |
| ForecastBench | 58 | — |

## Math

- DeepSeek-V3.1: 36.1 (#125)
- Gemini 1.5 Flash 8B: 13.3 (#296)

| Benchmark | DeepSeek-V3.1 | Gemini 1.5 Flash 8B |
|---|---|---|
| LMArena Math | 1420 | 1207 |
| OTIS Mock AIME 2024-2025 | — | 4.6% |

## Knowledge

- DeepSeek-V3.1: 43.0 (#86)
- Gemini 1.5 Flash 8B: 16.0 (#285)

| Benchmark | DeepSeek-V3.1 | Gemini 1.5 Flash 8B |
|---|---|---|
| LMArena Expert | 1403 | 1185 |
| GPQA Diamond | — | 33% |
| Vectara Hallucination Rate | 5.5% | — |

## Multimodal

- DeepSeek-V3.1: —
- Gemini 1.5 Flash 8B: 27.6 (#110)

| Benchmark | DeepSeek-V3.1 | Gemini 1.5 Flash 8B |
|---|---|---|
| LMArena Vision | — | 1044 |

## Multilingual

- DeepSeek-V3.1: 51.8 (#100)
- Gemini 1.5 Flash 8B: 38.6 (#224)

| Benchmark | DeepSeek-V3.1 | Gemini 1.5 Flash 8B |
|---|---|---|
| LMArena Non-English | 1400 | 1215 |
| LMArena Chinese | 1470 | 1231 |
| LMArena French | 1447 | 1233 |
| LMArena German | 1412 | 1206 |
| LMArena Japanese | 1374 | 1150 |
| LMArena Korean | 1337 | 1140 |
| LMArena Russian | 1405 | 1236 |
| LMArena Spanish | 1429 | 1212 |

## Instruction Following

- DeepSeek-V3.1: 74.1 (#105)
- Gemini 1.5 Flash 8B: 63.1 (#231)

| Benchmark | DeepSeek-V3.1 | Gemini 1.5 Flash 8B |
|---|---|---|
| LMArena Instruction Following | 1400 | 1199 |

## Long Context

- DeepSeek-V3.1: 36.3 (#227)
- Gemini 1.5 Flash 8B: 36.9 (#220)

| Benchmark | DeepSeek-V3.1 | Gemini 1.5 Flash 8B |
|---|---|---|
| LMArena Longer Query | 1422 | 1219 |
| Fiction.LiveBench | 52.8% | — |

## Writing & Preference

- DeepSeek-V3.1: 60.5 (#93)
- Gemini 1.5 Flash 8B: 43.0 (#227)

| Benchmark | DeepSeek-V3.1 | Gemini 1.5 Flash 8B |
|---|---|---|
| LMArena Text | 1420 | 1226 |
| LMArena Creative Writing | 1401 | 1218 |
| LMArena Multi-Turn | 1408 | 1185 |
| EQ-Bench Creative Writing | 1436 | — |

## FAQ

### Is DeepSeek-V3.1 better than Gemini 1.5 Flash 8B?

DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 29.7 on the Noometry Index.

### Is DeepSeek-V3.1 or Gemini 1.5 Flash 8B better for coding?

DeepSeek-V3.1 scores higher on coding benchmarks: 39.8 versus 34.9 in the Noometry coding category.

### How many benchmarks do DeepSeek-V3.1 and Gemini 1.5 Flash 8B share?

18 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Gemini 1.5 Flash 8B has 21.