Gemini 3.6 Flash vs GPT-4.1 Mini

Gemini 3.6 Flash leads GPT-4.1 Mini on the Artificial Analysis Intelligence Index, 34.0 to 10.2, and GPT-4.1 Mini costs 2.3x less per output token ($1.60 vs $3.75 per million). Updated October 21, 2026; 67 benchmarks have a result for both.

Replace Gemini 3.6 Flash Replace GPT-4.1 Mini

Gemini 3.6 FlashGoogle

Coding: 62.5
Overall: 68.3
Output $/M: $3.75

GPT-4.1 MiniOpenAI

Coding: No data
Overall: 31.9
Output $/M: $1.60

vs boards won of 67 shared

Gemini 3.6 Flash or GPT-4.1 Mini: which to pick

Only Gemini 3.6 Flash has a coding score, 62.5 on the Vibe Coding Index; GPT-4.1 Mini has none, so the two cannot be ranked on coding.

Pick GPT-4.1 Mini for output tokens 2.3x cheaper ($1.60 vs $3.75 per million).

Model AGemini 3.6 FlashGoogle62.5/1004 independent benchmarks$1.49 per solved task Model BGPT-4.1 MiniOpenAINot benchmarkedNo coding benchmark$1.818 per solved task

674219

Shared results: 67
Gemini 3.6 Flash only: 42
GPT-4.1 Mini only: 19
Like-for-like categories: 7 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

Coding
Vibe Coding Index, six public coding benchmarks
No call
Only Gemini 3.6 Flash has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
Gemini 3.6 Flash
Gemini 3.6 Flash leads, 34.0 against 10.2.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Gemini 3.6 Flash has a AA Agentic Index result, 29.0.
Directional only
Reasoning
GPQA Diamond
Gemini 3.6 Flash
Gemini 3.6 Flash leads, 93.4% against 67.9%.
Same board, both measured
Math
AIME
No call
Only GPT-4.1 Mini has a AIME result, 49.4%.
Directional only
Knowledge
MMLU Pro
Gemini 3.6 Flash
Gemini 3.6 Flash leads, 89.3% against 77.2%.
Same board, both measured
Web design
Design Arena: websites
Gemini 3.6 Flash
Gemini 3.6 Flash leads, 1300 against 997.
Same board, both measured
Long documents
Listed context window
Gemini 3.6 Flash
Gemini 3.6 Flash takes 1.05M tokens against 1.05M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GPT-4.1 Mini
Gemini 3.6 Flash $0.0026, GPT-4.1 Mini $0.0012 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Gemini 3.6 Flash
Gemini 3.6 Flash $1.49, GPT-4.1 Mini $1.818.
Published attempt cost and pass rate

At a glance

Coding index: Gemini 3.6 Flash 62.5 from 4 benchmarks, GPT-4.1 Mini not benchmarked.
Widest category: Math, 38.3 points apart on average over 4 shared benchmarks.
Widest single gap: ARC-AGI: Gemini 3.6 Flash 91.2% against GPT-4.1 Mini 3.5%, 87.7 points apart on a 0 to 100 scale.
Output price: Gemini 3.6 Flash $3.75 against GPT-4.1 Mini $1.60 per million output tokens, 2.3x apart.
Context window: Gemini 3.6 Flash takes 1.05M tokens, GPT-4.1 Mini 1.05M.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
Category	Gemini 3.6 Flash	Bars	GPT-4.1 Mini	Ties
Coding	5		0
Intelligence	2		0
Reasoning	14		0
Math	4		0
Knowledge	10		0
Web design	6		0
General	26		0
All shared boards	67		0

CodingLike-for-likeSix of these boards feed the Vibe Coding Index50

Coding benchmarks for Gemini 3.6 Flash and GPT-4.1 Mini
Benchmark	Gemini 3.6 Flash	GPT-4.1 Mini	Leader
Aider polyglot	Not measured	32.4%	Only GPT-4.1 Mini measured
SWE-bench Verified	Not measured	23.9%	Only GPT-4.1 Mini measured
LMArena WebDev	1538	Not measured	Only Gemini 3.6 Flash measured
AA Coding Index	69.2	20.2	Gemini 3.6 Flash
LiveCodeBench (Vals AI)	88.1%	58.2%	Gemini 3.6 Flash
SWE-bench Verified (Vals AI)	79.6%	Not measured	Only Gemini 3.6 Flash measured
Vibe Code Bench (Vals AI)	64.0%	Not measured	Only Gemini 3.6 Flash measured
Code migration (Vals AI)	30.9%	Not measured	Only Gemini 3.6 Flash measured
ProgramBench (Vals AI)	0.0%	Not measured	Only Gemini 3.6 Flash measured
IOI (Vals AI)	35.1%	Not measured	Only Gemini 3.6 Flash measured
Terminal-Bench 2.1 (Vals AI)	73.8%	Not measured	Only Gemini 3.6 Flash measured
CyberBench (Vals AI)	45.4%	Not measured	Only Gemini 3.6 Flash measured
LiveCodeBench (Artificial Analysis run)	Not measured	48.3%	Only GPT-4.1 Mini measured
SciCode	53.4%	Not measured	Only Gemini 3.6 Flash measured
Terminal-Bench Hard (Artificial Analysis run)	Not measured	7.6%	Only GPT-4.1 Mini measured
FrontierCode	34.4%	Not measured	Only Gemini 3.6 Flash measured
WeirdML	56.1%	37.6%	Gemini 3.6 Flash
ALE-Bench	715.5	Not measured	Only Gemini 3.6 Flash measured
LMArena Text: coding	1491	1367	Gemini 3.6 Flash
LMArena Text: software and IT	1492	1360	Gemini 3.6 Flash
LMArena WebDev: React	1528	Not measured	Only Gemini 3.6 Flash measured
LMArena WebDev: HTML	1547	Not measured	Only Gemini 3.6 Flash measured
LMArena WebDev: from an image	1545	Not measured	Only Gemini 3.6 Flash measured
SciCode	10.8%	Not measured	Only Gemini 3.6 Flash measured
Neither model has a result on the other 15 boards here

IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20

Intelligence benchmarks for Gemini 3.6 Flash and GPT-4.1 Mini
Benchmark	Gemini 3.6 Flash	GPT-4.1 Mini	Leader
AA Intelligence Index	34.0	10.2	Gemini 3.6 Flash
Epoch Capabilities Index	154.5	134.9	Gemini 3.6 Flash

Agentic workDirectional onlyPublic boards, shown as published, kept out of the index18 boards, none shared

Agentic work benchmarks for Gemini 3.6 Flash and GPT-4.1 Mini
Benchmark	Gemini 3.6 Flash	GPT-4.1 Mini	Leader
AA Agentic Index	29.0	Not measured	Only Gemini 3.6 Flash measured
Design Arena: agents building web apps	1197	Not measured	Only Gemini 3.6 Flash measured
Design Arena: agents building full-stack apps	1181	Not measured	Only Gemini 3.6 Flash measured
Design Arena: agents building mobile apps	1199	Not measured	Only Gemini 3.6 Flash measured
Design Arena: agents building Android apps	1203	Not measured	Only Gemini 3.6 Flash measured
Design Arena: agents building games	1181	Not measured	Only Gemini 3.6 Flash measured
Design Arena: HTML slides	1148	Not measured	Only Gemini 3.6 Flash measured
Design Arena: PowerPoint slides	1146	Not measured	Only Gemini 3.6 Flash measured
Design Arena: spreadsheets	1034	Not measured	Only Gemini 3.6 Flash measured
Finance Agent (Vals AI)	56.3%	Not measured	Only Gemini 3.6 Flash measured
Tax Agent Bench (Vals AI)	18.0%	Not measured	Only Gemini 3.6 Flash measured
Legal Research Bench (Vals AI)	25.0%	Not measured	Only Gemini 3.6 Flash measured
Excel Modeling Benchmark (Vals AI)	65.4%	Not measured	Only Gemini 3.6 Flash measured
BioMysteryBench (Vals AI)	58.5%	Not measured	Only Gemini 3.6 Flash measured
Terminal-Bench-Science (Vals AI)	4.3%	Not measured	Only Gemini 3.6 Flash measured
τ²-Bench Telecom	Not measured	52.9%	Only GPT-4.1 Mini measured
APEX-Agents	46.9%	Not measured	Only Gemini 3.6 Flash measured
Berkeley Function Calling Leaderboard (BFCL)	Not measured	50.4%	Only GPT-4.1 Mini measured
Neither model has a result on the other 23 boards here

ReasoningLike-for-likePublic boards, shown as published, kept out of the index140

Reasoning benchmarks for Gemini 3.6 Flash and GPT-4.1 Mini
Benchmark	Gemini 3.6 Flash	GPT-4.1 Mini	Leader
GPQA Diamond	93.4%	67.9%	Gemini 3.6 Flash
MMMU Pro (Vals AI)	88.4%	70.5%	Gemini 3.6 Flash
GPQA Diamond (Artificial Analysis run)	92.8%	66.4%	Gemini 3.6 Flash
Humanity's Last Exam (Artificial Analysis run)	40.8%	5.0%	Gemini 3.6 Flash
GPQA Diamond (Epoch AI run)	94.1%	65.8%	Gemini 3.6 Flash
ARC-AGI	91.2%	3.5%	Gemini 3.6 Flash
ARC-AGI-2	60.4%	0.0%	Gemini 3.6 Flash
Chess puzzles	42.0%	1.0%	Gemini 3.6 Flash
Mystery game puzzles	30.0%	7.0%	Gemini 3.6 Flash
LMArena Text: hard prompts	1486	1349	Gemini 3.6 Flash
LMArena Text: expert	1490	1338	Gemini 3.6 Flash
LMArena Text: hard prompts in English	1484	1362	Gemini 3.6 Flash
LMArena Vision: diagrams	1314	1182	Gemini 3.6 Flash
LMArena Vision: homework	1314	1214	Gemini 3.6 Flash
Kagi LLM Benchmark	Not measured	48.6%	Only GPT-4.1 Mini measured
Neither model has a result on the other 7 boards here

MathLike-for-likePublic boards, shown as published, kept out of the index40

Math benchmarks for Gemini 3.6 Flash and GPT-4.1 Mini
Benchmark	Gemini 3.6 Flash	GPT-4.1 Mini	Leader
AIME	Not measured	49.4%	Only GPT-4.1 Mini measured
MATH 500 (Vals AI)	Not measured	88.0%	Only GPT-4.1 Mini measured
MGSM (Vals AI)	Not measured	87.8%	Only GPT-4.1 Mini measured
AA Math Index	Not measured	46.3	Only GPT-4.1 Mini measured
AIME 2025 (Artificial Analysis run)	Not measured	46.3%	Only GPT-4.1 Mini measured
OTIS Mock AIME	94.2%	44.7%	Gemini 3.6 Flash
FrontierMath, tiers 1 to 3	58.9%	6.7%	Gemini 3.6 Flash
FrontierMath, tier 4	22.0%	Not measured	Only Gemini 3.6 Flash measured
ProofBench	36.0%	Not measured	Only Gemini 3.6 Flash measured
MATH level 5	Not measured	87.3%	Only GPT-4.1 Mini measured
LMArena Text: math	1508	1343	Gemini 3.6 Flash
LMArena Text: mathematical work	1492	1347	Gemini 3.6 Flash
Neither model has a result on the other 1 board here

KnowledgeLike-for-likePublic boards, shown as published, kept out of the index100

Knowledge benchmarks for Gemini 3.6 Flash and GPT-4.1 Mini
Benchmark	Gemini 3.6 Flash	GPT-4.1 Mini	Leader
MMLU Pro	89.3%	77.2%	Gemini 3.6 Flash
LegalBench (Vals AI)	86.7%	78.0%	Gemini 3.6 Flash
CorpFin (Vals AI)	63.3%	57.9%	Gemini 3.6 Flash
TaxEval (Vals AI)	74.9%	71.9%	Gemini 3.6 Flash
MortgageTax (Vals AI)	67.6%	65.5%	Gemini 3.6 Flash
MedQA (Vals AI)	Not measured	84.6%	Only GPT-4.1 Mini measured
MedCode (Vals AI)	53.1%	Not measured	Only Gemini 3.6 Flash measured
MMLU Pro (Artificial Analysis run)	Not measured	78.1%	Only GPT-4.1 Mini measured
SimpleQA Verified	66.2%	12.7%	Gemini 3.6 Flash
LMArena Text: science	1489	1328	Gemini 3.6 Flash
LMArena Text: medicine and healthcare	1469	1324	Gemini 3.6 Flash
LMArena Text: legal and government	1479	1343	Gemini 3.6 Flash
LMArena Text: business and finance	1464	1322	Gemini 3.6 Flash
FACTS Benchmark Suite	65.3%	Not measured	Only Gemini 3.6 Flash measured
Neither model has a result on the other 4 boards here

Web designLike-for-likePublic boards, shown as published, kept out of the index60

Web design benchmarks for Gemini 3.6 Flash and GPT-4.1 Mini
Benchmark	Gemini 3.6 Flash	GPT-4.1 Mini	Leader
Design Arena: websites	1300	997	Gemini 3.6 Flash
Design Arena: UI components	1297	961	Gemini 3.6 Flash
Design Arena: game dev	1263	1071	Gemini 3.6 Flash
Design Arena: data viz	1289	1034	Gemini 3.6 Flash
Design Arena: 3D	1272	837	Gemini 3.6 Flash
Design Arena: all code categories	1290	994	Gemini 3.6 Flash
Design Arena: ASCII art	1281	Not measured	Only Gemini 3.6 Flash measured
Neither model has a result on the other 2 boards here

GeneralLike-for-likePublic boards, shown as published, kept out of the index260

General benchmarks for Gemini 3.6 Flash and GPT-4.1 Mini
Benchmark	Gemini 3.6 Flash	GPT-4.1 Mini	Leader
Public Benefits Bench (Vals AI)	56.6%	Not measured	Only Gemini 3.6 Flash measured
SAGE (Vals AI)	48.7%	Not measured	Only Gemini 3.6 Flash measured
MedScribe (Vals AI)	79.7%	Not measured	Only Gemini 3.6 Flash measured
Vals Multimodal Index	65.1%	Not measured	Only Gemini 3.6 Flash measured
IFBench	Not measured	38.3%	Only GPT-4.1 Mini measured
Long context reasoning (AA-LCR)	80.0%	44.0%	Gemini 3.6 Flash
DTBench	95.5%	68.8%	Gemini 3.6 Flash
LMCA	44.9%	21.1%	Gemini 3.6 Flash
Fiction.LiveBench	Not measured	44.4%	Only GPT-4.1 Mini measured
Furniture assembly	23.3%	Not measured	Only Gemini 3.6 Flash measured
LMArena Text	1480	1341	Gemini 3.6 Flash
LMArena Text: instruction following	1467	1333	Gemini 3.6 Flash
LMArena Text: creative writing	1466	1299	Gemini 3.6 Flash
LMArena Vision	1299	1181	Gemini 3.6 Flash
LMArena Text: English	1482	1356	Gemini 3.6 Flash
LMArena Text: non-English	1470	1318	Gemini 3.6 Flash
LMArena Text: Chinese	1531	1329	Gemini 3.6 Flash
LMArena Text: German	1480	1350	Gemini 3.6 Flash
LMArena Text: Japanese	1475	1290	Gemini 3.6 Flash
LMArena Text: Korean	1429	1298	Gemini 3.6 Flash
LMArena Text: French	1503	1358	Gemini 3.6 Flash
LMArena Text: Spanish	1476	1319	Gemini 3.6 Flash
LMArena Text: Russian	1488	1324	Gemini 3.6 Flash
LMArena Text: Polish	1473	1326	Gemini 3.6 Flash
LMArena Text: multi-turn	1481	1354	Gemini 3.6 Flash
LMArena Text: longer queries	1475	1344	Gemini 3.6 Flash
LMArena Text: writing and language	1470	1319	Gemini 3.6 Flash
LMArena Text: entertainment and media	1456	1300	Gemini 3.6 Flash
LMArena Vision: English	1295	1191	Gemini 3.6 Flash
LMArena Vision: Chinese	1357	1186	Gemini 3.6 Flash
LMArena Vision: reading text	1312	1188	Gemini 3.6 Flash
LMArena Vision: humor	1289	1182	Gemini 3.6 Flash
LMArena Vision: captioning	Not measured	1174	Only GPT-4.1 Mini measured
LMArena Vision: recognizing things	Not measured	1187	Only GPT-4.1 Mini measured
LMArena Vision: creative writing	1278	1182	Gemini 3.6 Flash
LMArena Document	1456	Not measured	Only Gemini 3.6 Flash measured
Neither model has a result on the other 10 boards here

Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared

Image generation benchmarks for Gemini 3.6 Flash and GPT-4.1 Mini
Benchmark	Gemini 3.6 Flash	GPT-4.1 Mini	Leader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

Gemini 3.6 Flash$0.0026Fits in one request

GPT-4.1 Mini$0.0012Fits in one request

GPT-4.1 Mini costs less

Repository review

50K input + 3K output tokens

Gemini 3.6 Flash$0.049Fits in one request

GPT-4.1 Mini$0.025Fits in one request

GPT-4.1 Mini costs less

Agent loop

200K input + 10K output tokens

Gemini 3.6 Flash$0.188Fits in one request

GPT-4.1 Mini$0.096Fits in one request

GPT-4.1 Mini costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of Gemini 3.6 Flash and GPT-4.1 Mini
Specification	Google Gemini 3.6 Flash	OpenAI GPT-4.1 Mini
Maker	Google	OpenAI
Weights	No public weights listed	No public weights listed
Released	July 21, 2026	April 14, 2025
Context window	1.05M	1.05M
Input $/Mtok	$0.75	$0.40
Output $/Mtok	$3.75	$1.60
Coding index	62.5	Not benchmarked
Independent measurements behind it	4	0
Cost per solved task	$1.49	$1.818
Source	OpenRouter listing	OpenRouter listing

Questions

Is Gemini 3.6 Flash better than GPT-4.1 Mini for coding?

Only Gemini 3.6 Flash has a coding score, 62.5 on the Vibe Coding Index; GPT-4.1 Mini has none, so the two cannot be ranked on coding. Pick GPT-4.1 Mini for output tokens 2.3x cheaper ($1.60 vs $3.75 per million).

Which is cheaper, Gemini 3.6 Flash or GPT-4.1 Mini?

Gemini 3.6 Flash costs $0.75 per million input tokens and $3.75 per million output tokens; GPT-4.1 Mini costs $0.40 and $1.60. Per solved SWE-bench Verified task, Gemini 3.6 Flash costs $1.49 and GPT-4.1 Mini $1.818.

Which has the bigger context window, Gemini 3.6 Flash or GPT-4.1 Mini?

Gemini 3.6 Flash, with 1.05M tokens against 1.05M.

How many benchmarks is the Gemini 3.6 Flash vs GPT-4.1 Mini comparison based on?

67 benchmarks have a result for both models as of October 21, 2026. Gemini 3.6 Flash's coding index rests on 4 independent benchmarks and GPT-4.1 Mini's on 0. Where only one model has a result, the page says so instead of naming a winner.

Gemini 3.6 Flash or GPT-4.1 Mini: which to pick

Which one for your work

Coding

Intelligence

Agentic work

Reasoning

Math

Knowledge

Web design

Long documents

Everyday cost

Cost per solved task

At a glance

Benchmark by benchmark

What each workload costs

Chat turn

Repository review

Agent loop

Specification differences

Questions

Compare next