# DeepSeek LLM 67B vs Gemini 2.5 Flash-Lite

> Gemini 2.5 Flash-Lite is the stronger model overall, scoring 37.0 to 24.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-llm-67b-vs-gemini-2-5-flash-lite
- Last updated: 2026-10-12
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Gemini 2.5 Flash-Lite in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 2.5 Flash-Lite leads 38.0 to 8.7.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek LLM 67B | Gemini 2.5 Flash-Lite |
|---|---|---|
| Provider | DeepSeek | Google |
| Noometry Index | 24.9 | 37.0 |
| Rank | 347 | 211 |
| Context | — | 1.05M |
| Input $/M | — | $0.10 |
| Output $/M | — | $0.40 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek LLM 67B: 31.9 (#278)
- Gemini 2.5 Flash-Lite: 38.5 (#173)

| Benchmark | DeepSeek LLM 67B | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Coding | 1096 | 1373 |
| WeirdML | — | 35.2% |
| ALE-Bench | — | 325.9 |

## Agentic & Tool Use

- DeepSeek LLM 67B: —
- Gemini 2.5 Flash-Lite: 28.0 (#96)

| Benchmark | DeepSeek LLM 67B | Gemini 2.5 Flash-Lite |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 36.9% |

## Reasoning

- DeepSeek LLM 67B: 16.5 (#304)
- Gemini 2.5 Flash-Lite: 22.2 (#205)

| Benchmark | DeepSeek LLM 67B | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1377 |
| Epoch Capabilities Index | 110.5 | 133.94 |
| Kagi LLM Benchmark | — | 40.5% |
| Chess Puzzles | 0% | — |
| DTBench | — | 62.8% |
| LMCA | — | 18.1% |

## Math

- DeepSeek LLM 67B: 8.7 (#324)
- Gemini 2.5 Flash-Lite: 38.0 (#144)

| Benchmark | DeepSeek LLM 67B | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Math | 1108 | 1373 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| Omni-MATH | — | 48% |
| MATH Level 5 | 6.4% | — |

## Knowledge

- DeepSeek LLM 67B: 7.0 (#313)
- Gemini 2.5 Flash-Lite: 32.5 (#210)

| Benchmark | DeepSeek LLM 67B | Gemini 2.5 Flash-Lite |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| MMLU-Pro | — | 53.7% |
| Vectara Hallucination Rate | — | 3.3% |
| GPQA (HELM) | — | 30.9% |
| LMArena Expert | — | 1373 |

## Multimodal

- DeepSeek LLM 67B: —
- Gemini 2.5 Flash-Lite: 29.1 (#114)

| Benchmark | DeepSeek LLM 67B | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Vision | — | 1198 |
| VPCT | — | 30% |

## Multilingual

- DeepSeek LLM 67B: 29.4 (#267)
- Gemini 2.5 Flash-Lite: 49.3 (#134)

| Benchmark | DeepSeek LLM 67B | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Non-English | 1073 | 1369 |
| LMArena Chinese | 1132 | 1404 |
| LMArena French | — | 1388 |
| LMArena German | — | 1389 |
| LMArena Japanese | — | 1359 |
| LMArena Korean | — | 1360 |
| LMArena Russian | — | 1373 |
| LMArena Spanish | — | 1396 |

## Instruction Following

- DeepSeek LLM 67B: 55.4 (#277)
- Gemini 2.5 Flash-Lite: 70.0 (#168)

| Benchmark | DeepSeek LLM 67B | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Instruction Following | 1079 | 1367 |
| IFEval | — | 81% |

## Long Context

- DeepSeek LLM 67B: 33.1 (#265)
- Gemini 2.5 Flash-Lite: 33.3 (#262)

| Benchmark | DeepSeek LLM 67B | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Longer Query | 1092 | 1373 |
| Fiction.LiveBench | — | 47.2% |

## Writing & Preference

- DeepSeek LLM 67B: 31.6 (#282)
- Gemini 2.5 Flash-Lite: 56.8 (#135)

| Benchmark | DeepSeek LLM 67B | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Text | 1105 | 1379 |
| LMArena Creative Writing | 1067 | 1367 |
| LMArena Multi-Turn | 1082 | 1366 |
| WildBench | — | 81.8% |

## FAQ

### Is DeepSeek LLM 67B better than Gemini 2.5 Flash-Lite?

Gemini 2.5 Flash-Lite is the stronger model overall, scoring 37.0 to 24.9 on the Noometry Index.

### Is DeepSeek LLM 67B or Gemini 2.5 Flash-Lite better for coding?

Gemini 2.5 Flash-Lite scores higher on coding benchmarks: 38.5 versus 31.9 in the Noometry coding category.

### How many benchmarks do DeepSeek LLM 67B and Gemini 2.5 Flash-Lite share?

11 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Gemini 2.5 Flash-Lite has 33.