# DeepSeek-V2.5 (Sep 2024) vs Gemini 3.5 Flash Lite

> Gemini 3.5 Flash Lite is the stronger model overall, scoring 41.8 to 37.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v2-5-vs-gemini-3-5-flash-lite
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 1 category and Gemini 3.5 Flash Lite in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 3.5 Flash Lite leads 50.0 to 34.2.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek-V2.5 (Sep 2024) | Gemini 3.5 Flash Lite |
|---|---|---|
| Provider | DeepSeek | Google |
| Noometry Index | 37.0 | 41.8 |
| Rank | 197 | 113 |
| Context | — | 1.05M |
| Input $/M | — | $0.30 |
| Output $/M | — | $2.50 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek-V2.5 (Sep 2024): 31.3 (#274)
- Gemini 3.5 Flash Lite: 42.1 (#96)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 3.5 Flash Lite |
|---|---|---|
| LMArena Coding | 1310 | 1455 |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1440 |
| SciCode | — | 41.3% |
| WeirdML | — | 39% |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| ALE-Bench | — | 765.27 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |

## Agentic & Tool Use

- DeepSeek-V2.5 (Sep 2024): —
- Gemini 3.5 Flash Lite: 28.6 (#82)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 3.5 Flash Lite |
|---|---|---|
| GDP.pdf | — | 10% |

## Reasoning

- DeepSeek-V2.5 (Sep 2024): 24.5 (#145)
- Gemini 3.5 Flash Lite: 27.8 (#95)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 3.5 Flash Lite |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1441 |
| ARC-AGI-2 | — | 10.3% |
| NYT Connections (extended) | — | 60.4% |
| ARC-AGI-1 | — | 53.5% |
| CritPt | — | 0% |
| Chess Puzzles | — | 22% |
| Mystery Game Puzzles | — | 19% |
| DTBench | — | 83.5% |
| LMCA | — | 37.6% |
| Epoch Capabilities Index | — | 145.12 |

## Math

- DeepSeek-V2.5 (Sep 2024): 33.3 (#177)
- Gemini 3.5 Flash Lite: 25.7 (#245)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 3.5 Flash Lite |
|---|---|---|
| LMArena Math | 1289 | 1431 |
| FrontierMath (Tiers 1-3) | — | 26% |
| FrontierMath Tier 4 | — | 0% |
| OTIS Mock AIME 2024-2025 | — | 71.1% |
| ProofBench | — | 13% |

## Knowledge

- DeepSeek-V2.5 (Sep 2024): 34.2 (#190)
- Gemini 3.5 Flash Lite: 50.0 (#66)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 3.5 Flash Lite |
|---|---|---|
| LMArena Expert | 1266 | 1430 |
| GPQA Diamond | — | 83.3% |

## Multimodal

- DeepSeek-V2.5 (Sep 2024): —
- Gemini 3.5 Flash Lite: 40.3 (#38)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 3.5 Flash Lite |
|---|---|---|
| LMArena Vision | — | 1266 |

## Multilingual

- DeepSeek-V2.5 (Sep 2024): 42.7 (#188)
- Gemini 3.5 Flash Lite: 53.8 (#59)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 3.5 Flash Lite |
|---|---|---|
| LMArena Non-English | 1273 | 1428 |
| LMArena Chinese | 1317 | 1467 |
| LMArena French | 1288 | 1452 |
| LMArena German | 1258 | 1454 |
| LMArena Japanese | 1228 | 1428 |
| LMArena Korean | 1209 | 1406 |
| LMArena Russian | 1289 | 1443 |
| LMArena Spanish | 1248 | 1440 |

## Instruction Following

- DeepSeek-V2.5 (Sep 2024): 67.7 (#189)
- Gemini 3.5 Flash Lite: 75.0 (#77)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 3.5 Flash Lite |
|---|---|---|
| LMArena Instruction Following | 1280 | 1420 |

## Long Context

- DeepSeek-V2.5 (Sep 2024): 39.5 (#169)
- Gemini 3.5 Flash Lite: 43.8 (#80)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 3.5 Flash Lite |
|---|---|---|
| LMArena Longer Query | 1301 | 1435 |

## Writing & Preference

- DeepSeek-V2.5 (Sep 2024): 50.0 (#182)
- Gemini 3.5 Flash Lite: 64.4 (#55)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 3.5 Flash Lite |
|---|---|---|
| LMArena Text | 1294 | 1436 |
| LMArena Creative Writing | 1285 | 1419 |
| LMArena Multi-Turn | 1297 | 1445 |
| EQ-Bench Creative Writing | — | 1559 |

## FAQ

### Is DeepSeek-V2.5 (Sep 2024) better than Gemini 3.5 Flash Lite?

Gemini 3.5 Flash Lite is the stronger model overall, scoring 41.8 to 37.0 on the Noometry Index.

### Is DeepSeek-V2.5 (Sep 2024) or Gemini 3.5 Flash Lite better for coding?

Gemini 3.5 Flash Lite scores higher on coding benchmarks: 42.1 versus 31.3 in the Noometry coding category.

### How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Gemini 3.5 Flash Lite share?

17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Gemini 3.5 Flash Lite has 38.