# DeepSeek-V3.1 vs Gemini 2.0 Flash-Lite

> DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 37.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v3-1-vs-gemini-2-0-flash-lite
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 7 categories and Gemini 2.0 Flash-Lite in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1 leads 60.5 to 51.9.
- The biggest single-benchmark swing is DTBench: 82.7% for DeepSeek-V3.1 and 52.5% for Gemini 2.0 Flash-Lite.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek-V3.1 | Gemini 2.0 Flash-Lite |
|---|---|---|
| Provider | DeepSeek | Google |
| Noometry Index | 42.2 | 37.3 |
| Rank | 106 | 189 |
| Context | 164K | — |
| Input $/M | $0.25 | — |
| Output $/M | $0.95 | — |
| Weights | Open | Proprietary |

## Coding

- DeepSeek-V3.1: 39.8 (#140)
- Gemini 2.0 Flash-Lite: 37.4 (#181)

| Benchmark | DeepSeek-V3.1 | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Coding | 1417 | 1322 |
| WeirdML | 38.4% | — |
| LiveBench Coding | — | 47.1% |

## Reasoning

- DeepSeek-V3.1: 27.3 (#109)
- Gemini 2.0 Flash-Lite: 21.2 (#203)

| Benchmark | DeepSeek-V3.1 | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1324 |
| DTBench | 82.7% | 52.5% |
| ForecastBench | 58 | 57.1 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| LiveBench Reasoning | — | 50.1% |
| LiveBench Data Analysis | — | 65.5% |
| LMCA | 24.3% | — |
| Epoch Capabilities Index | 139.92 | — |
| LiveBench | — | 54.3% |

## Math

- DeepSeek-V3.1: 36.1 (#125)
- Gemini 2.0 Flash-Lite: 31.8 (#192)

| Benchmark | DeepSeek-V3.1 | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Math | 1420 | 1309 |
| Omni-MATH | — | 37.4% |
| LiveBench Math | — | 58.1% |

## Knowledge

- DeepSeek-V3.1: 43.0 (#86)
- Gemini 2.0 Flash-Lite: 34.6 (#185)

| Benchmark | DeepSeek-V3.1 | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Expert | 1403 | 1305 |
| MMLU-Pro | — | 72% |
| Vectara Hallucination Rate | 5.5% | — |
| GPQA (HELM) | — | 50% |

## Multimodal

- DeepSeek-V3.1: —
- Gemini 2.0 Flash-Lite: 30.6 (#103)

| Benchmark | DeepSeek-V3.1 | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Vision | — | 1100 |

## Multilingual

- DeepSeek-V3.1: 51.8 (#100)
- Gemini 2.0 Flash-Lite: 46.2 (#156)

| Benchmark | DeepSeek-V3.1 | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Non-English | 1400 | 1323 |
| LMArena Chinese | 1470 | 1339 |
| LMArena French | 1447 | 1346 |
| LMArena German | 1412 | 1306 |
| LMArena Japanese | 1374 | 1302 |
| LMArena Korean | 1337 | 1325 |
| LMArena Russian | 1405 | 1328 |
| LMArena Spanish | 1429 | 1313 |

## Instruction Following

- DeepSeek-V3.1: 74.1 (#105)
- Gemini 2.0 Flash-Lite: 70.6 (#158)

| Benchmark | DeepSeek-V3.1 | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Instruction Following | 1400 | 1305 |
| LiveBench Instruction Following | — | 78.3% |
| IFEval | — | 82.4% |

## Long Context

- DeepSeek-V3.1: 36.3 (#227)
- Gemini 2.0 Flash-Lite: 40.1 (#155)

| Benchmark | DeepSeek-V3.1 | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Longer Query | 1422 | 1321 |
| Fiction.LiveBench | 52.8% | — |

## Writing & Preference

- DeepSeek-V3.1: 60.5 (#93)
- Gemini 2.0 Flash-Lite: 51.9 (#172)

| Benchmark | DeepSeek-V3.1 | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Text | 1420 | 1330 |
| LMArena Creative Writing | 1401 | 1319 |
| LMArena Multi-Turn | 1408 | 1307 |
| EQ-Bench Creative Writing | 1436 | — |
| WildBench | — | 79% |
| LiveBench Language | — | 34.3% |

## FAQ

### Is DeepSeek-V3.1 better than Gemini 2.0 Flash-Lite?

DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 37.3 on the Noometry Index.

### Is DeepSeek-V3.1 or Gemini 2.0 Flash-Lite better for coding?

DeepSeek-V3.1 scores higher on coding benchmarks: 39.8 versus 37.4 in the Noometry coding category.

### How many benchmarks do DeepSeek-V3.1 and Gemini 2.0 Flash-Lite share?

19 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Gemini 2.0 Flash-Lite has 32.