LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Gemini 2.5 Flash vs GPT-5 Mini

Updated October 21, 2026. 67 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Gemini 2.5 Flash Replace GPT-5 Mini
Gemini 2.5 FlashGoogle
Coding
28.7
Overall
15.5
Output $/M
$2.50
41
GPT-5 MiniOpenAI
Coding
59.8
Overall
20.6
Output $/M
$2.00
26
vs boards won of 67 shared

Decision reading

Pick GPT-5 Mini for coding: it scores 59.8 on the Vibe Coding Index against 28.7 for Gemini 2.5 Flash.

Pick Gemini 2.5 Flash when the context window is larger, 1.05M against 400K tokens, or when what matters is LMArena Text: coding or LMArena Text: software and IT, where it leads.

Model AGemini 2.5 FlashGoogle28.7/1001 independent benchmark$0.466 per solved taskModel BGPT-5 MiniOpenAI59.8/1001 independent benchmark$0.08 per solved task
Shared results
67
Gemini 2.5 Flash only
2
GPT-5 Mini only
31
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 2.5 Flash 28.7 from 1 benchmark, GPT-5 Mini 59.8 from 1 benchmark.
Widest category
Agentic work, 21.5 points apart on average over 2 shared benchmarks.
Widest single gap
τ²-Bench Telecom: Gemini 2.5 Flash 31.6% against GPT-5 Mini 71.1%, 39.5 points apart on a 0 to 100 scale.
Output price
Gemini 2.5 Flash $2.50 against GPT-5 Mini $2.00 per million output tokens, 1.3x apart.
Context window
Gemini 2.5 Flash takes 1.05M tokens, GPT-5 Mini 400K.

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 2.5 FlashBarsGPT-5 MiniTies
Coding24
Intelligence02
Agentic work11
Reasoning54
Math22
Knowledge42
Web design07
General274
All shared boards4126
CodingLike-for-likeFour of these boards feed the Vibe Coding Index24
Coding benchmarks for Gemini 2.5 Flash and GPT-5 Mini
BenchmarkGemini 2.5 FlashGPT-5 MiniLeader
SWE-bench Verified28.7%59.8%GPT-5 Mini
SWE-bench MultilingualNot measured39.7%Only GPT-5 Mini measured
LiveCodeBench (Vals AI)Not measured86.6%Only GPT-5 Mini measured
SWE-bench Verified (Vals AI)Not measured60.8%Only GPT-5 Mini measured
Vibe Code Bench (Vals AI)Not measured14.2%Only GPT-5 Mini measured
LiveCodeBench (Artificial Analysis run)69.5%83.8%GPT-5 Mini
SciCodeNot measured39.0%Only GPT-5 Mini measured
Terminal-Bench Hard (Artificial Analysis run)13.6%33.3%GPT-5 Mini
Terminal-Bench17.1%34.8%GPT-5 Mini
WeirdMLNot measured52.7%Only GPT-5 Mini measured
LMArena Text: coding14231406Gemini 2.5 Flash
LMArena Text: software and IT14251394Gemini 2.5 Flash
Neither model has a result on the other 26 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Gemini 2.5 Flash and GPT-5 Mini
BenchmarkGemini 2.5 FlashGPT-5 MiniLeader
AA Intelligence Index15.520.6GPT-5 Mini
Epoch Capabilities Index142.9145.3GPT-5 Mini
Agentic workLike-for-likePublic boards, shown as published, kept out of the index11
Agentic work benchmarks for Gemini 2.5 Flash and GPT-5 Mini
BenchmarkGemini 2.5 FlashGPT-5 MiniLeader
τ²-Bench Telecom31.6%71.1%GPT-5 Mini
BALROG33.5%Not measuredOnly Gemini 2.5 Flash measured
Vending-Bench 2$549-$31Gemini 2.5 Flash
Neither model has a result on the other 36 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index54
Reasoning benchmarks for Gemini 2.5 Flash and GPT-5 Mini
BenchmarkGemini 2.5 FlashGPT-5 MiniLeader
GPQA DiamondNot measured80.3%Only GPT-5 Mini measured
MMMU Pro (Vals AI)Not measured78.9%Only GPT-5 Mini measured
GPQA Diamond (Artificial Analysis run)79.0%82.8%GPT-5 Mini
Humanity's Last Exam (Artificial Analysis run)12.1%21.5%GPT-5 Mini
GPQA Diamond (Epoch AI run)Not measured75.0%Only GPT-5 Mini measured
ARC-AGI33.3%54.3%GPT-5 Mini
ARC-AGI-22.5%4.4%GPT-5 Mini
SimpleBench41.2%Not measuredOnly Gemini 2.5 Flash measured
Chess puzzlesNot measured24.0%Only GPT-5 Mini measured
Mystery game puzzlesNot measured10.0%Only GPT-5 Mini measured
VPCTNot measured40.2%Only GPT-5 Mini measured
LMArena Text: hard prompts14221380Gemini 2.5 Flash
LMArena Text: expert14261379Gemini 2.5 Flash
LMArena Text: hard prompts in English14201383Gemini 2.5 Flash
LMArena Vision: diagrams12451202Gemini 2.5 Flash
LMArena Vision: homework12441210Gemini 2.5 Flash
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index22
Math benchmarks for Gemini 2.5 Flash and GPT-5 Mini
BenchmarkGemini 2.5 FlashGPT-5 MiniLeader
AIMENot measured91.5%Only GPT-5 Mini measured
MATH 500 (Vals AI)Not measured94.8%Only GPT-5 Mini measured
MGSM (Vals AI)Not measured92.6%Only GPT-5 Mini measured
AA Math Index73.390.7GPT-5 Mini
AIME 2025 (Artificial Analysis run)73.3%90.7%GPT-5 Mini
OTIS Mock AIMENot measured86.7%Only GPT-5 Mini measured
FrontierMath, tiers 1 to 3Not measured46.7%Only GPT-5 Mini measured
FrontierMath, tier 4Not measured12.2%Only GPT-5 Mini measured
ProofBenchNot measured9.0%Only GPT-5 Mini measured
MATH level 5Not measured97.8%Only GPT-5 Mini measured
LMArena Text: math14111378Gemini 2.5 Flash
LMArena Text: mathematical work14221380Gemini 2.5 Flash
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index42
Knowledge benchmarks for Gemini 2.5 Flash and GPT-5 Mini
BenchmarkGemini 2.5 FlashGPT-5 MiniLeader
MMLU ProNot measured82.2%Only GPT-5 Mini measured
LegalBench (Vals AI)Not measured81.8%Only GPT-5 Mini measured
CaseLaw (Vals AI)Not measured68.5%Only GPT-5 Mini measured
CorpFin (Vals AI)Not measured60.2%Only GPT-5 Mini measured
TaxEval (Vals AI)Not measured75.2%Only GPT-5 Mini measured
MortgageTax (Vals AI)Not measured66.9%Only GPT-5 Mini measured
MedQA (Vals AI)Not measured96.1%Only GPT-5 Mini measured
MedCode (Vals AI)40.4%43.0%GPT-5 Mini
MMLU Pro (Artificial Analysis run)83.2%83.7%GPT-5 Mini
SimpleQA VerifiedNot measured21.6%Only GPT-5 Mini measured
LMArena Text: science14331371Gemini 2.5 Flash
LMArena Text: medicine and healthcare14281380Gemini 2.5 Flash
LMArena Text: legal and government14301375Gemini 2.5 Flash
LMArena Text: business and finance14041358Gemini 2.5 Flash
Neither model has a result on the other 3 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index07
Web design benchmarks for Gemini 2.5 Flash and GPT-5 Mini
BenchmarkGemini 2.5 FlashGPT-5 MiniLeader
Design Arena: websites10741125GPT-5 Mini
Design Arena: UI components10051106GPT-5 Mini
Design Arena: game dev10051130GPT-5 Mini
Design Arena: data viz10601131GPT-5 Mini
Design Arena: 3D10211037GPT-5 Mini
Design Arena: all code categories10591115GPT-5 Mini
Design Arena: SVG10181091GPT-5 Mini
Design Arena: ASCII artNot measured1124Only GPT-5 Mini measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index274
General benchmarks for Gemini 2.5 Flash and GPT-5 Mini
BenchmarkGemini 2.5 FlashGPT-5 MiniLeader
SAGE (Vals AI)44.8%43.0%Gemini 2.5 Flash
MedScribe (Vals AI)83.0%80.6%Gemini 2.5 Flash
IFBench50.3%75.4%GPT-5 Mini
Long context reasoning (AA-LCR)65.3%72.3%GPT-5 Mini
DTBench76.5%80.5%GPT-5 Mini
LMCA27.5%34.2%GPT-5 Mini
Fiction.LiveBenchNot measured69.4%Only GPT-5 Mini measured
Creative writing (Lech Mazur)Not measured83.1%Only GPT-5 Mini measured
LMArena Text14171373Gemini 2.5 Flash
LMArena Text: instruction following14051357Gemini 2.5 Flash
LMArena Text: creative writing14001325Gemini 2.5 Flash
LMArena Vision12351202Gemini 2.5 Flash
LMArena Text: English14181379Gemini 2.5 Flash
LMArena Text: non-English14091363Gemini 2.5 Flash
LMArena Text: Chinese14491386Gemini 2.5 Flash
LMArena Text: German14171366Gemini 2.5 Flash
LMArena Text: Japanese13961341Gemini 2.5 Flash
LMArena Text: Korean13851308Gemini 2.5 Flash
LMArena Text: French14321386Gemini 2.5 Flash
LMArena Text: Spanish14221354Gemini 2.5 Flash
LMArena Text: Russian14151362Gemini 2.5 Flash
LMArena Text: Polish14131378Gemini 2.5 Flash
LMArena Text: multi-turn14081363Gemini 2.5 Flash
LMArena Text: longer queries14191355Gemini 2.5 Flash
LMArena Text: writing and language14051344Gemini 2.5 Flash
LMArena Text: entertainment and media13931340Gemini 2.5 Flash
LMArena Vision: English12391216Gemini 2.5 Flash
LMArena Vision: Chinese12841214Gemini 2.5 Flash
LMArena Vision: reading text12371199Gemini 2.5 Flash
LMArena Vision: humor12251205Gemini 2.5 Flash
LMArena Vision: captioning12771217Gemini 2.5 Flash
LMArena Vision: recognizing things12521226Gemini 2.5 Flash
LMArena Vision: creative writing12411181Gemini 2.5 Flash
Neither model has a result on the other 13 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemini 2.5 Flash and GPT-5 Mini
BenchmarkGemini 2.5 FlashGPT-5 MiniLeader
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 2.5 Flash$0.0015Fits in one request
GPT-5 Mini$0.0013Fits in one request

GPT-5 Mini costs less

Repository review

50K input + 3K output tokens

Gemini 2.5 Flash$0.022Fits in one request
GPT-5 Mini$0.018Fits in one request

GPT-5 Mini costs less

Agent loop

200K input + 10K output tokens

Gemini 2.5 Flash$0.085Fits in one request
GPT-5 Mini$0.070Fits in one request

GPT-5 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 2.5 Flash and GPT-5 Mini
SpecificationGoogle Gemini 2.5 FlashOpenAI GPT-5 Mini
MakerGoogleOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedJune 17, 2025August 7, 2025
Context window1.05M400K
Input $/Mtok$0.30$0.25
Output $/Mtok$2.50$2.00
Coding index28.759.8
Independent measurements behind it11
Cost per solved task$0.466$0.08
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemini 2.5 Flash better than GPT-5 Mini for coding?

Pick GPT-5 Mini for coding: it scores 59.8 on the Vibe Coding Index against 28.7 for Gemini 2.5 Flash. Pick Gemini 2.5 Flash when the context window is larger, 1.05M against 400K tokens, or when what matters is LMArena Text: coding or LMArena Text: software and IT, where it leads.

Which is cheaper, Gemini 2.5 Flash or GPT-5 Mini?

Gemini 2.5 Flash costs $0.30 per million input tokens and $2.50 per million output tokens; GPT-5 Mini costs $0.25 and $2.00. Per solved SWE-bench Verified task, Gemini 2.5 Flash costs $0.466 and GPT-5 Mini $0.08.

Which has the bigger context window, Gemini 2.5 Flash or GPT-5 Mini?

Gemini 2.5 Flash, with 1.05M tokens against 400K.

How many benchmarks is the Gemini 2.5 Flash vs GPT-5 Mini comparison based on?

67 benchmarks have a result for both models as of October 21, 2026. Gemini 2.5 Flash's coding index rests on 1 independent benchmark and GPT-5 Mini's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next