Model comparison

Gemini 3 Flash Preview vs GPT-4.1 mini

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 33.6 on the Noometry Index. GPT-4.1 mini costs 1.6× less per token, which makes it the better buy when Gemini 3 Flash Preview's lead doesn't matter for your workload.

Last verified October 10, 2026. 32 shared benchmarks.

Gemini 3 Flash Preview

Google

52.3

Rank #40 Confirmed

GPT-4.1 mini OpenAI

33.6

Rank #240 Confirmed

Summary

They share 32 benchmarks with published results for both. Gemini 3 Flash Preview scores higher in 10 categories and GPT-4.1 mini in 0 categories; 10 gaps are clear of the uncertainty.
The widest gap is in reasoning, where Gemini 3 Flash Preview leads 49.2 to 10.8.
The biggest single-benchmark swing is ARC-AGI-1: 84.7% for Gemini 3 Flash Preview and 3.5% for GPT-4.1 mini.
GPT-4.1 mini is cheaper at $0.40 / $1.60 per million input/output tokens, against $0.50 / $3 for Gemini 3 Flash Preview.
Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 1.05M.

Side by side

Gemini 3 Flash Preview and GPT-4.1 mini specifications
	Gemini 3 Flash Preview	GPT-4.1 mini
Provider	Google	OpenAI
Noometry Index	52.3	33.6
Released	2025-12-17	2025-04-14
Weights	Proprietary	Proprietary
Context window	1.05M	1.05M
Max output	66K	33K
Input $ / M tokens	$0.50	$0.40
Output $ / M tokens	$3	$1.60
Results tracked	59	47

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

Category by category

Coding Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 50.9 (#42), GPT-4.1 mini: 30.6 (#293)

Coding benchmarks
Benchmark	Gemini 3 Flash Preview	GPT-4.1 mini
SWE-bench Verified (bash only)	75.8%	23.9%
WeirdML	61.6%	37.6%
LMArena Coding	1460	1367
SWE-bench Verified	75.4%	—
Aider Polyglot	—	32.4%
LMArena WebDev	1439	—
SWE-bench Multilingual	72.7%	—
SciCode	—	40.4%
GSO	9.8%	—
BigCodeBench Instruct	—	48.9%
CadEval	—	16%
ALE-Bench	1,367	—

Agentic & Tool Use Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 38.7 (#29), GPT-4.1 mini: 33.3 (#55)

Agentic & Tool Use benchmarks
Benchmark	Gemini 3 Flash Preview	GPT-4.1 mini
Terminal-Bench	64.3%	—
Berkeley Function Calling Leaderboard	—	50.5%
τ²-bench Airline	82.5%	—
τ²-bench Banking	27.3%	—
τ²-bench Retail	76.8%	—
τ²-bench Telecom	91.2%	—
DeepResearch Bench	49.8%	—
BALROG	48.1%	—
GDP.pdf	10%	—
LMArena Search	1198	—
Vending-Bench 2	3,635	—

Reasoning Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 49.2 (#37), GPT-4.1 mini: 10.8 (#340)

Reasoning benchmarks
Benchmark	Gemini 3 Flash Preview	GPT-4.1 mini
ARC-AGI-2	33.6%	0%
ARC-AGI-1	84.7%	3.5%
Chess Puzzles	40%	7%
LMArena Hard Prompts	1465	1349
Mystery Game Puzzles	26%	7%
DTBench	89.1%	68.8%
LMCA	43.1%	21.1%
Epoch Capabilities Index	151.8	135.01
SimpleBench	61.1%	—
Kagi LLM Benchmark	—	48.6%
NYT Connections (extended)	83.1%	—
CritPt	—	0%
ForecastBench	58.5	—

Math Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 51.7 (#55), GPT-4.1 mini: 24.1 (#270)

Math benchmarks
Benchmark	Gemini 3 Flash Preview	GPT-4.1 mini
FrontierMath (Tiers 1-3)	51.2%	6.7%
OTIS Mock AIME 2024-2025	95.6%	44.7%
LMArena Math	1473	1343
FrontierMath (Feb 2025 set)	35.6%	4.5%
FrontierMath Tier 4	17.1%	—
MathArena Final-Answer Competitions	67.6%	—
ProofBench	15%	—
Omni-MATH	—	49.1%
MATH Level 5	—	87.3%
FrontierMath Tier 4 (v1)	4.2%	—

Knowledge Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 58.8 (#33), GPT-4.1 mini: 34.7 (#194)

Knowledge benchmarks
Benchmark	Gemini 3 Flash Preview	GPT-4.1 mini
GPQA Diamond	89.4%	65.8%
SimpleQA Verified	66.8%	12.7%
LMArena Expert	1462	1338
MMLU-Pro	—	78.3%
Vectara Hallucination Rate	13.5%	—
GPQA (HELM)	—	61.4%

Multimodal Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 45.5 (#16), GPT-4.1 mini: 35.8 (#82)

Multimodal benchmarks
Benchmark	Gemini 3 Flash Preview	GPT-4.1 mini
LMArena Vision	1285	1181
GeoBench	88%	—
VPCT	72.6%	—
Blueprint-Bench 2	0%	—
LMArena Document	1413	—

Multilingual Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 55.7 (#27), GPT-4.1 mini: 45.7 (#166)

Multilingual benchmarks
Benchmark	Gemini 3 Flash Preview	GPT-4.1 mini
LMArena Non-English	1458	1318
LMArena Chinese	1511	1329
LMArena French	1477	1358
LMArena German	1497	1351
LMArena Japanese	1489	1290
LMArena Korean	1443	1298
LMArena Russian	1480	1324
LMArena Spanish	1469	1319

Instruction Following Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 75.7 (#56), GPT-4.1 mini: 73.7 (#118)

Instruction Following benchmarks
Benchmark	Gemini 3 Flash Preview	GPT-4.1 mini
LMArena Instruction Following	1437	1333
IFEval	—	90.4%

Long Context Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 44.4 (#67), GPT-4.1 mini: 31.8 (#275)

Long Context benchmarks
Benchmark	Gemini 3 Flash Preview	GPT-4.1 mini
LMArena Longer Query	1452	1344
Fiction.LiveBench	—	44.4%

Writing & Preference Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 65.5 (#45), GPT-4.1 mini: 48.6 (#199)

Writing & Preference benchmarks
Benchmark	Gemini 3 Flash Preview	GPT-4.1 mini
LMArena Text	1466	1340
LMArena Creative Writing	1457	1300
LMArena Multi-Turn	1471	1354
EQ-Bench Creative Writing	—	1147
WildBench	—	83.8%

Frequently asked questions

Is Gemini 3 Flash Preview better than GPT-4.1 mini?

Which is cheaper, Gemini 3 Flash Preview or GPT-4.1 mini?

GPT-4.1 mini is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; Gemini 3 Flash Preview lists at $0.50 and $3.

Is Gemini 3 Flash Preview or GPT-4.1 mini better for coding?

Gemini 3 Flash Preview scores higher on coding benchmarks: 50.9 versus 30.6 in the Noometry coding category.

Which has the bigger context window?

Gemini 3 Flash Preview does, with 1.05M tokens against 1.05M.

How many benchmarks do Gemini 3 Flash Preview and GPT-4.1 mini share?

32 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and GPT-4.1 mini has 47.