Model comparison

DeepSeek V4.1 Flash vs Gemini 3.1 Flash Lite

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 40.8 on the Noometry Index.

Last verified October 12, 2026. 29 shared benchmarks.

DeepSeek V4.1 Flash

DeepSeek

52.8

Rank #38 Confirmed

Gemini 3.1 Flash Lite

Google

40.8

Rank #144 Confirmed

Summary

They share 29 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 9 categories and Gemini 3.1 Flash Lite in 1 category; 9 gaps are clear of the uncertainty.
The widest gap is in reasoning, where DeepSeek V4.1 Flash leads 50.2 to 22.9.
The biggest single-benchmark swing is NYT Connections (extended): 89.6% for DeepSeek V4.1 Flash and 8.2% for Gemini 3.1 Flash Lite.
DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.25 / $1.50 for Gemini 3.1 Flash Lite.
Gemini 3.1 Flash Lite accepts more context: 1.05M tokens versus 1M.
DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.

Side by side

DeepSeek V4.1 Flash and Gemini 3.1 Flash Lite specifications
	DeepSeek V4.1 Flash	Gemini 3.1 Flash Lite
Provider	DeepSeek	Google
Noometry Index	52.8	40.8
Released	2026-09-09	2026-03-03
Weights	Open	Proprietary
Context window	1M	1.05M
Max output	393K	66K
Input $ / M tokens	$0.15	$0.25
Output $ / M tokens	$0.60	$1.50
Results tracked	37	38

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

Category by category

Coding DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 52.9 (#32), Gemini 3.1 Flash Lite: 37.8 (#188)

Coding benchmarks
Benchmark	DeepSeek V4.1 Flash	Gemini 3.1 Flash Lite
LMArena WebDev	1619	1256
SciCode	51.9%	41.9%
LMArena Coding	1506	1400
ALE-Bench	1,092	797.73
WeirdML	—	52.2%

Agentic & Tool Use DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 31.2 (#69), Gemini 3.1 Flash Lite: 30.2 (#79)

Agentic & Tool Use benchmarks
Benchmark	DeepSeek V4.1 Flash	Gemini 3.1 Flash Lite
APEX-Agents	39.5%	—
DeepResearch Bench	—	37.3%
GDP.pdf	19.8%	—

Reasoning DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 50.2 (#36), Gemini 3.1 Flash Lite: 22.9 (#186)

Reasoning benchmarks
Benchmark	DeepSeek V4.1 Flash	Gemini 3.1 Flash Lite
NYT Connections (extended)	89.6%	8.2%
CritPt	14.3%	1.1%
LMArena Hard Prompts	1483	1407
DTBench	89.9%	76.8%
LMCA	47%	35%
Epoch Capabilities Index	154.9	144.47
Kagi LLM Benchmark	—	67.2%
Chess Puzzles	—	25%
EnigmaEval	—	3%
Thematic Generalization	—	63.3%
Mystery Game Puzzles	43%	—
Surface Evolver Bench	46.3%	—
ForecastBench	—	54.4

Math DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 66.7 (#25), Gemini 3.1 Flash Lite: 40.7 (#90)

Math benchmarks
Benchmark	DeepSeek V4.1 Flash	Gemini 3.1 Flash Lite
FrontierMath (Tiers 1-3)	67.4%	27.7%
OTIS Mock AIME 2024-2025	98.3%	80%
LMArena Math	1477	1428
FrontierMath Tier 4	26.8%	—
ProofBench	54%	—

Knowledge DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 57.9 (#38), Gemini 3.1 Flash Lite: 41.9 (#104)

Knowledge benchmarks
Benchmark	DeepSeek V4.1 Flash	Gemini 3.1 Flash Lite
GPQA Diamond	89.8%	81.8%
LMArena Expert	1506	1398
Humanity's Last Exam	—	8.6%
Vectara Hallucination Rate	—	8.2%

Multimodal Too close to call

DeepSeek V4.1 Flash: 39.1 (#61), Gemini 3.1 Flash Lite: 39.4 (#60)

Multimodal benchmarks
Benchmark	DeepSeek V4.1 Flash	Gemini 3.1 Flash Lite
LMArena Vision	1277	1240
Furniture Assembly	34.2%	—

Multilingual DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 55.0 (#35), Gemini 3.1 Flash Lite: 52.3 (#86)

Multilingual benchmarks
Benchmark	DeepSeek V4.1 Flash	Gemini 3.1 Flash Lite
LMArena Non-English	1448	1411
LMArena Chinese	1497	1461
LMArena French	1452	1424
LMArena German	1484	1429
LMArena Japanese	1412	1413
LMArena Korean	1452	1392
LMArena Russian	1471	1420
LMArena Spanish	1459	1421

Instruction Following DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 77.3 (#26), Gemini 3.1 Flash Lite: 72.7 (#131)

Instruction Following benchmarks
Benchmark	DeepSeek V4.1 Flash	Gemini 3.1 Flash Lite
LMArena Instruction Following	1474	1377

Long Context DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 45.2 (#47), Gemini 3.1 Flash Lite: 42.5 (#122)

Long Context benchmarks
Benchmark	DeepSeek V4.1 Flash	Gemini 3.1 Flash Lite
LMArena Longer Query	1475	1394

Writing & Preference DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 65.4 (#48), Gemini 3.1 Flash Lite: 60.9 (#94)

Writing & Preference benchmarks
Benchmark	DeepSeek V4.1 Flash	Gemini 3.1 Flash Lite
LMArena Text	1462	1416
LMArena Creative Writing	1435	1401
LMArena Multi-Turn	1457	1417
EQ-Bench Creative Writing	1540	—

Frequently asked questions

Is DeepSeek V4.1 Flash better than Gemini 3.1 Flash Lite?

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 40.8 on the Noometry Index.

Which is cheaper, DeepSeek V4.1 Flash or Gemini 3.1 Flash Lite?

DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Gemini 3.1 Flash Lite lists at $0.25 and $1.50.

Is DeepSeek V4.1 Flash or Gemini 3.1 Flash Lite better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 37.8 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.1 Flash Lite does, with 1.05M tokens against 1M.

How many benchmarks do DeepSeek V4.1 Flash and Gemini 3.1 Flash Lite share?

29 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and Gemini 3.1 Flash Lite has 38.