LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Gemini 3.8 Flash vs MiniMax M3

Updated October 21, 2026. 105 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Gemini 3.8 Flash Replace MiniMax M3
Gemini 3.8 FlashGoogle
Coding
70.5
Overall
40.9
Output $/M
$4.125
98
MiniMax M3MiniMax
Coding
57.8
Overall
29.2
Output $/M
$1.20
7
vs boards won of 105 shared

Decision reading

Pick Gemini 3.8 Flash for coding: it scores 70.5 on the Vibe Coding Index against 57.8 for MiniMax M3.

Pick MiniMax M3 when output tokens cost 3.4x less, or when a solved task costs $0.56 against $2.74.

Model AGemini 3.8 FlashGoogle70.5/1002 independent benchmarks$2.74 per solved taskModel BMiniMax M3MiniMax57.8/1002 independent benchmarks$0.56 per solved task
Shared results
105
Gemini 3.8 Flash only
21
MiniMax M3 only
11
Like-for-like categories
8 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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.

At a glance

Coding index
Gemini 3.8 Flash 70.5 from 2 benchmarks, MiniMax M3 57.8 from 2 benchmarks.
Widest category
Math, 21.7 points apart on average over 4 shared benchmarks.
Widest single gap
LiveBench browser: Gemini 3.8 Flash 64.0% against MiniMax M3 8.0%, 56.0 points apart on a 0 to 100 scale.
Output price
Gemini 3.8 Flash $4.125 against MiniMax M3 $1.20 per million output tokens, 3.4x apart.
Context window
Both take 1.05M tokens.

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
CategoryGemini 3.8 FlashBarsMiniMax M3Ties
Coding201
Intelligence20
Agentic work142
Reasoning130
Math40
Knowledge81
Web design90
General283
All shared boards987
CodingLike-for-likeFour of these boards feed the Vibe Coding Index201
Coding benchmarks for Gemini 3.8 Flash and MiniMax M3
BenchmarkGemini 3.8 FlashMiniMax M3Leader
LiveBench coding82.2%70.9%Gemini 3.8 Flash
LMArena WebDev15851482Gemini 3.8 Flash
AA Coding Index76.358.6Gemini 3.8 Flash
LiveCodeBench (Vals AI)89.5%82.2%Gemini 3.8 Flash
SWE-bench Verified (Vals AI)80.0%75.0%Gemini 3.8 Flash
Terminal-Bench 4 (Vals AI)19.7%1.0%Gemini 3.8 Flash
Vibe Code Bench (Vals AI)78.7%47.6%Gemini 3.8 Flash
Code migration (Vals AI)36.5%19.9%Gemini 3.8 Flash
ProgramBench (Vals AI)1.0%Not measuredOnly Gemini 3.8 Flash measured
IOI (Vals AI)56.9%Not measuredOnly Gemini 3.8 Flash measured
Terminal-Bench 2.1 (Vals AI)81.3%53.6%Gemini 3.8 Flash
SWE-bench Multimodal (Vals AI)40.8%33.3%Gemini 3.8 Flash
Vibe Code Bench 1-100 (Vals AI)18.8%9.2%Gemini 3.8 Flash
SkillsBench (Vals AI)58.0%51.5%Gemini 3.8 Flash
CyberBench (Vals AI)43.8%65.0%MiniMax M3
SciCode56.6%47.1%Gemini 3.8 Flash
Terminal-Bench Hard (Artificial Analysis run)Not measured42.4%Only MiniMax M3 measured
FrontierCode41.2%14.7%Gemini 3.8 Flash
FrontierSWE19.6%Not measuredOnly Gemini 3.8 Flash measured
WeirdML84.8%Not measuredOnly Gemini 3.8 Flash measured
ALE-Bench1269.7640.0Gemini 3.8 Flash
LMArena Text: coding15081470Gemini 3.8 Flash
LMArena Text: software and IT15071466Gemini 3.8 Flash
LMArena WebDev: React15771478Gemini 3.8 Flash
LMArena WebDev: HTML16161455Gemini 3.8 Flash
LMArena WebDev: from an image15931470Gemini 3.8 Flash
Neither model has a result on the other 12 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Gemini 3.8 Flash and MiniMax M3
BenchmarkGemini 3.8 FlashMiniMax M3Leader
AA Intelligence Index40.929.2Gemini 3.8 Flash
Epoch Capabilities Index157.4146.9Gemini 3.8 Flash
Agentic workLike-for-likePublic boards, shown as published, kept out of the index142
Agentic work benchmarks for Gemini 3.8 Flash and MiniMax M3
BenchmarkGemini 3.8 FlashMiniMax M3Leader
AA Agentic Index40.229.5Gemini 3.8 Flash
Design Arena: agents building web apps12381200Gemini 3.8 Flash
Design Arena: agents building full-stack apps12441197Gemini 3.8 Flash
Design Arena: agents building mobile apps12361169Gemini 3.8 Flash
Design Arena: agents building Android apps10781164MiniMax M3
Design Arena: agents building Godot games1273Not measuredOnly Gemini 3.8 Flash measured
Design Arena: agents building gamesNot measured1158Only MiniMax M3 measured
Design Arena: HTML slidesNot measured1180Only MiniMax M3 measured
Design Arena: PowerPoint slides11781205MiniMax M3
Design Arena: spreadsheets10521021Gemini 3.8 Flash
LiveBench research79.1%68.0%Gemini 3.8 Flash
LiveBench browser64.0%8.0%Gemini 3.8 Flash
LiveBench long agentic30.1%12.4%Gemini 3.8 Flash
SREBench (Vals AI)11.1%Not measuredOnly Gemini 3.8 Flash measured
Finance Agent (Vals AI)61.4%48.3%Gemini 3.8 Flash
Tax Agent Bench (Vals AI)32.1%20.6%Gemini 3.8 Flash
Legal Research Bench (Vals AI)38.9%29.8%Gemini 3.8 Flash
Harvey's Legal Agent Benchmark (Vals AI)12.1%Not measuredOnly Gemini 3.8 Flash measured
Excel Modeling Benchmark (Vals AI)72.2%47.8%Gemini 3.8 Flash
BioMysteryBench (Vals AI)62.2%Not measuredOnly Gemini 3.8 Flash measured
Terminal-Bench-Science (Vals AI)8.6%Not measuredOnly Gemini 3.8 Flash measured
Vals Science Index35.8%Not measuredOnly Gemini 3.8 Flash measured
Time Horizon Index (Vals AI)18.8%Not measuredOnly Gemini 3.8 Flash measured
CUA-bench (Vals AI)4.2%Not measuredOnly Gemini 3.8 Flash measured
τ²-Bench TelecomNot measured88.9%Only MiniMax M3 measured
APEX-Agents64.3%37.7%Gemini 3.8 Flash
Remote Labor Index5.8%Not measuredOnly Gemini 3.8 Flash measured
OSWorld 2.0Not measured4.6%Only MiniMax M3 measured
Vending-Bench 2$5,094$2,158Gemini 3.8 Flash
Neither model has a result on the other 10 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index130
Reasoning benchmarks for Gemini 3.8 Flash and MiniMax M3
BenchmarkGemini 3.8 FlashMiniMax M3Leader
GPQA Diamond94.4%92.7%Gemini 3.8 Flash
LiveBench reasoning89.3%74.5%Gemini 3.8 Flash
MysteryMechanism (Vals AI)36.5%Not measuredOnly Gemini 3.8 Flash measured
MMMU Pro (Vals AI)89.1%81.2%Gemini 3.8 Flash
GPQA Diamond (Artificial Analysis run)95.3%92.9%Gemini 3.8 Flash
Humanity's Last Exam (Artificial Analysis run)47.8%39.0%Gemini 3.8 Flash
GPQA Diamond (Epoch AI run)95.4%90.9%Gemini 3.8 Flash
ARC-AGI98.5%Not measuredOnly Gemini 3.8 Flash measured
ARC-AGI-289.2%Not measuredOnly Gemini 3.8 Flash measured
SimpleBenchNot measured45.8%Only MiniMax M3 measured
Chess puzzles58.0%13.0%Gemini 3.8 Flash
Mystery game puzzles47.0%8.0%Gemini 3.8 Flash
LMArena Text: hard prompts15091447Gemini 3.8 Flash
LMArena Text: expert15261461Gemini 3.8 Flash
LMArena Text: hard prompts in English15041455Gemini 3.8 Flash
LMArena Vision: diagrams13451266Gemini 3.8 Flash
LMArena Vision: homework13511268Gemini 3.8 Flash
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index40
Math benchmarks for Gemini 3.8 Flash and MiniMax M3
BenchmarkGemini 3.8 FlashMiniMax M3Leader
OTIS Mock AIME98.9%71.1%Gemini 3.8 Flash
FrontierMath, tiers 1 to 368.4%Not measuredOnly Gemini 3.8 Flash measured
FrontierMath, tier 422.0%Not measuredOnly Gemini 3.8 Flash measured
ProofBench48.0%18.0%Gemini 3.8 Flash
LMArena Text: math15321429Gemini 3.8 Flash
LMArena Text: mathematical work15191448Gemini 3.8 Flash
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index81
Knowledge benchmarks for Gemini 3.8 Flash and MiniMax M3
BenchmarkGemini 3.8 FlashMiniMax M3Leader
MMLU Pro90.2%84.2%Gemini 3.8 Flash
LegalBench (Vals AI)87.0%85.4%Gemini 3.8 Flash
CorpFin (Vals AI)Not measured68.1%Only MiniMax M3 measured
TaxEval (Vals AI)74.5%72.7%Gemini 3.8 Flash
MortgageTax (Vals AI)65.3%68.4%MiniMax M3
MedCode (Vals AI)48.1%46.3%Gemini 3.8 Flash
SimpleQA Verified69.7%Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: science15231452Gemini 3.8 Flash
LMArena Text: medicine and healthcare15081441Gemini 3.8 Flash
LMArena Text: legal and government14971437Gemini 3.8 Flash
LMArena Text: business and finance14791434Gemini 3.8 Flash
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index90
Web design benchmarks for Gemini 3.8 Flash and MiniMax M3
BenchmarkGemini 3.8 FlashMiniMax M3Leader
Design Arena: websites13011257Gemini 3.8 Flash
Design Arena: UI components13181246Gemini 3.8 Flash
Design Arena: game dev13051210Gemini 3.8 Flash
Design Arena: data viz12691235Gemini 3.8 Flash
Design Arena: 3D12951209Gemini 3.8 Flash
Design Arena: all code categories13041247Gemini 3.8 Flash
Design Arena: SVG12951161Gemini 3.8 Flash
Design Arena: ASCII art12641161Gemini 3.8 Flash
LiveBench design72.7%66.2%Gemini 3.8 Flash
GeneralLike-for-likePublic boards, shown as published, kept out of the index283
General benchmarks for Gemini 3.8 Flash and MiniMax M3
BenchmarkGemini 3.8 FlashMiniMax M3Leader
Vals Index56.0%Not measuredOnly Gemini 3.8 Flash measured
LiveBench data analysis54.0%76.2%MiniMax M3
Public Benefits Bench (Vals AI)65.3%64.1%Gemini 3.8 Flash
SAGE (Vals AI)35.1%50.6%MiniMax M3
MedScribe (Vals AI)84.5%87.3%MiniMax M3
Vals Multimodal IndexNot measured60.0%Only MiniMax M3 measured
IFBenchNot measured82.9%Only MiniMax M3 measured
Long context reasoning (AA-LCR)84.0%83.0%Gemini 3.8 Flash
DTBench95.7%78.9%Gemini 3.8 Flash
LMCA52.9%33.7%Gemini 3.8 Flash
Surface Evolver Bench76.9%55.0%Gemini 3.8 Flash
Furniture assembly31.7%Not measuredOnly Gemini 3.8 Flash measured
LMArena Text14991433Gemini 3.8 Flash
LMArena Text: instruction following14921433Gemini 3.8 Flash
LMArena Text: creative writing14881404Gemini 3.8 Flash
LMArena Vision13151251Gemini 3.8 Flash
LMArena Text: English14981443Gemini 3.8 Flash
LMArena Text: non-English14911420Gemini 3.8 Flash
LMArena Text: Chinese15531466Gemini 3.8 Flash
LMArena Text: German15011428Gemini 3.8 Flash
LMArena Text: Japanese15071380Gemini 3.8 Flash
LMArena Text: Korean14641373Gemini 3.8 Flash
LMArena Text: French14961444Gemini 3.8 Flash
LMArena Text: Spanish14871433Gemini 3.8 Flash
LMArena Text: Russian15141426Gemini 3.8 Flash
LMArena Text: Polish14971423Gemini 3.8 Flash
LMArena Text: multi-turn15031443Gemini 3.8 Flash
LMArena Text: longer queries15071446Gemini 3.8 Flash
LMArena Text: writing and language14941419Gemini 3.8 Flash
LMArena Text: entertainment and media14801403Gemini 3.8 Flash
LMArena Vision: English13181263Gemini 3.8 Flash
LMArena Vision: Chinese14161311Gemini 3.8 Flash
LMArena Vision: reading text13331259Gemini 3.8 Flash
LMArena Vision: humor13211235Gemini 3.8 Flash
LMArena Vision: recognizing thingsNot measured1197Only MiniMax M3 measured
LMArena Vision: creative writing12991234Gemini 3.8 Flash
LMArena DocumentNot measured1435Only MiniMax M3 measured
Neither model has a result on the other 9 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemini 3.8 Flash and MiniMax M3
BenchmarkGemini 3.8 FlashMiniMax M3Leader
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 3.8 Flash$0.0029Fits in one request
MiniMax M3$0.0009Fits in one request

MiniMax M3 costs less

Repository review

50K input + 3K output tokens

Gemini 3.8 Flash$0.054Fits in one request
MiniMax M3$0.019Fits in one request

MiniMax M3 costs less

Agent loop

200K input + 10K output tokens

Gemini 3.8 Flash$0.206Fits in one request
MiniMax M3$0.072Fits in one request

MiniMax M3 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 3.8 Flash and MiniMax M3
SpecificationGoogle Gemini 3.8 FlashMiniMax M3
MakerGoogleMiniMax
WeightsNo public weights listedOpen weights
ReleasedSeptember 2, 2026May 31, 2026
Context window1.05M1.05M
Input $/Mtok$0.825$0.30
Output $/Mtok$4.125$1.20
Coding index70.557.8
Independent measurements behind it22
Cost per solved task$2.74$0.56
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemini 3.8 Flash better than MiniMax M3 for coding?

Pick Gemini 3.8 Flash for coding: it scores 70.5 on the Vibe Coding Index against 57.8 for MiniMax M3. Pick MiniMax M3 when output tokens cost 3.4x less, or when a solved task costs $0.56 against $2.74.

Which is cheaper, Gemini 3.8 Flash or MiniMax M3?

Gemini 3.8 Flash costs $0.825 per million input tokens and $4.125 per million output tokens; MiniMax M3 costs $0.30 and $1.20. Per solved SWE-bench Verified task, Gemini 3.8 Flash costs $2.74 and MiniMax M3 $0.56.

Which has the bigger context window, Gemini 3.8 Flash or MiniMax M3?

Neither: both take 1.05M tokens.

How many benchmarks is the Gemini 3.8 Flash vs MiniMax M3 comparison based on?

105 benchmarks have a result for both models as of October 21, 2026. Gemini 3.8 Flash's coding index rests on 2 independent benchmarks and MiniMax M3's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/gemini-3-8-flash-vs-minimax-minimax-m3" title="Gemini 3.8 Flash vs MiniMax M3, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/gemini-3-8-flash-vs-minimax-minimax-m3">LLMBenchmark.ai, Gemini 3.8 Flash vs MiniMax M3</a></p>