Noometry

Model comparison

DeepSeek Coder 6.7B vs Gemini 2.0 Flash-Lite

Gemini 2.0 Flash-Lite has enough public results to be ranked (#194); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

DeepSeek Coder 6.7B DeepSeek

37.6

Unranked Sparse

Gemini 2.0 Flash-Lite Google

37.8

Rank #194 Confirmed

Summary

  • DeepSeek Coder 6.7B has downloadable open weights; the other is API-only.

Side by side

DeepSeek Coder 6.7BGemini 2.0 Flash-Lite
ProviderDeepSeekGoogle
Noometry Index37.637.8
Released2023-11-022025-02-05
WeightsOpenProprietary
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked932

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Gemini 2.0 Flash-Lite leads

DeepSeek Coder 6.7B: 35.8 (#219), Gemini 2.0 Flash-Lite: 37.9 (#185)

BenchmarkDeepSeek Coder 6.7BGemini 2.0 Flash-Lite
BigCodeBench Instruct35.5%—
LiveBench Coding—47.1%
LMArena Coding—1322
BigCodeBench Complete43.8%—
HumanEval+71.3%—
MBPP+65.6%—

Reasoning Not comparable

DeepSeek Coder 6.7B: —, Gemini 2.0 Flash-Lite: 22.0 (#210)

BenchmarkDeepSeek Coder 6.7BGemini 2.0 Flash-Lite
LiveBench Reasoning—50.1%
LMArena Hard Prompts—1324
DTBench—52.5%
LiveBench Data Analysis—65.5%
Epoch Capabilities Index89.62—
ForecastBench—57.1
LiveBench—54.3%
WinoGrande57.6%—

Math Not comparable

DeepSeek Coder 6.7B: —, Gemini 2.0 Flash-Lite: 34.1 (#196)

BenchmarkDeepSeek Coder 6.7BGemini 2.0 Flash-Lite
Omni-MATH—37.4%
LiveBench Math—58.1%
LMArena Math—1309
GSM8K21.3%—

Knowledge Not comparable

DeepSeek Coder 6.7B: —, Gemini 2.0 Flash-Lite: 35.0 (#189)

BenchmarkDeepSeek Coder 6.7BGemini 2.0 Flash-Lite
MMLU-Pro—72%
GPQA (HELM)—50%
LMArena Expert—1305
ARC (AI2) Challenge36.4%—
MMLU36.4%—

Multimodal Not comparable

DeepSeek Coder 6.7B: —, Gemini 2.0 Flash-Lite: 31.2 (#109)

BenchmarkDeepSeek Coder 6.7BGemini 2.0 Flash-Lite
LMArena Vision—1100

Multilingual Not comparable

DeepSeek Coder 6.7B: —, Gemini 2.0 Flash-Lite: 46.0 (#161)

BenchmarkDeepSeek Coder 6.7BGemini 2.0 Flash-Lite
LMArena Non-English—1323
LMArena Chinese—1339
LMArena French—1347
LMArena German—1306
LMArena Japanese—1301
LMArena Korean—1325
LMArena Russian—1328
LMArena Spanish—1313

Instruction Following Not comparable

DeepSeek Coder 6.7B: —, Gemini 2.0 Flash-Lite: 70.4 (#163)

BenchmarkDeepSeek Coder 6.7BGemini 2.0 Flash-Lite
LiveBench Instruction Following—78.3%
IFEval—82.4%
LMArena Instruction Following—1305

Long Context Not comparable

DeepSeek Coder 6.7B: —, Gemini 2.0 Flash-Lite: 40.1 (#160)

BenchmarkDeepSeek Coder 6.7BGemini 2.0 Flash-Lite
LMArena Longer Query—1320

Writing & Preference Not comparable

DeepSeek Coder 6.7B: —, Gemini 2.0 Flash-Lite: 51.7 (#177)

BenchmarkDeepSeek Coder 6.7BGemini 2.0 Flash-Lite
LMArena Text—1330
LMArena Creative Writing—1319
WildBench—79%
LMArena Multi-Turn—1307
LiveBench Language—34.3%

Frequently asked questions

Is DeepSeek Coder 6.7B better than Gemini 2.0 Flash-Lite?

Gemini 2.0 Flash-Lite has enough public results to be ranked (#194); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.

Is DeepSeek Coder 6.7B or Gemini 2.0 Flash-Lite better for coding?

Gemini 2.0 Flash-Lite scores higher on coding benchmarks: 37.9 versus 35.8 in the Noometry coding category.

How many benchmarks do DeepSeek Coder 6.7B and Gemini 2.0 Flash-Lite share?

0 benchmarks have published results for both models. DeepSeek Coder 6.7B has 9 scored results on Noometry and Gemini 2.0 Flash-Lite has 32.

Related comparisons

Go deeper