Enter opens the highlighted result. Esc closes.

Gemini 2.5 Pro vs GPT-5

GPT-5 leads Gemini 2.5 Pro on coding, 38.8 to 19.1 on the Vibe Coding Index, at about the same output price ($10.00 vs $10.00 per million). Updated October 21, 2026; 85 benchmarks have a result for both.

Replace Gemini 2.5 Pro Replace GPT-5
Gemini 2.5 ProGoogle
Coding
19.1
Overall
41.8
Output $/M
$10.00
42
GPT-5OpenAI
Coding
38.8
Overall
51.5
Output $/M
$10.00
42
vs boards won of 85 shared, 1 tied

Gemini 2.5 Pro or GPT-5: which to pick

Pick GPT-5 for coding: it scores 38.8 on the Vibe Coding Index against 19.1 for Gemini 2.5 Pro.

Pick Gemini 2.5 Pro for a larger context window (1.05M against 400K tokens) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.

Model AGemini 2.5 ProGoogle19.1/1003 independent benchmarks$0.64 per solved taskModel BGPT-5OpenAI38.8/1003 independent benchmarks$0.39 per solved task
Shared results
85
Gemini 2.5 Pro only
5
GPT-5 only
28
Like-for-like categories
8 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.

At a glance

Coding index
Gemini 2.5 Pro 19.1 from 3 benchmarks, GPT-5 38.8 from 3 benchmarks.
Widest category
Agentic work, 25.6 points apart on average over 4 shared benchmarks.
Widest single gap
BrowseComp-Plus: Gemini 2.5 Pro 29.5% against GPT-5 80.0%, 50.5 points apart on a 0 to 100 scale.
Output price
Both cost $10.00 per million output tokens.
Context window
Gemini 2.5 Pro takes 1.05M tokens, GPT-5 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 ProBarsGPT-5Ties
Coding211
Intelligence02
Agentic work04
Reasoning56
Math25
Knowledge73
Web design141 tie
General257
All shared boards42421 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index211
Coding benchmarks for Gemini 2.5 Pro and GPT-5
BenchmarkGemini 2.5 ProGPT-5Leader
Aider polyglotNot measured88.0%Only GPT-5 measured
SWE-bench Verified53.6%74.4%GPT-5
LMArena WebDev12261418GPT-5
AA Coding Index33.337.8GPT-5
LiveCodeBench (Vals AI)Not measured85.9%Only GPT-5 measured
SWE-bench Verified (Vals AI)54.4%69.0%GPT-5
Vibe Code Bench (Vals AI)0.4%20.1%GPT-5
LiveCodeBench (Artificial Analysis run)80.1%84.6%GPT-5
SciCode46.3%Not measuredOnly Gemini 2.5 Pro measured
Terminal-Bench Hard (Artificial Analysis run)26.5%37.9%GPT-5
Terminal-Bench32.6%49.6%GPT-5
GSO-Bench3.9%6.9%GPT-5
WeirdML54.0%60.7%GPT-5
ALE-BenchNot measured807.6Only GPT-5 measured
LMArena Text: coding14521436Gemini 2.5 Pro
LMArena Text: software and IT14591420Gemini 2.5 Pro
LMArena WebDev: HTML12351427GPT-5
LMArena WebDev: from an image1285Not measuredOnly Gemini 2.5 Pro measured
SciCodeNot measured0.0%Only GPT-5 measured
Neither model has a result on the other 20 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Gemini 2.5 Pro and GPT-5
BenchmarkGemini 2.5 ProGPT-5Leader
AA Intelligence Index16.123.0GPT-5
Epoch Capabilities Index145.1150.0GPT-5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index04
Agentic work benchmarks for Gemini 2.5 Pro and GPT-5
BenchmarkGemini 2.5 ProGPT-5Leader
AA Agentic Index1.6Not measuredOnly Gemini 2.5 Pro measured
τ²-Bench Telecom54.1%86.5%GPT-5
METR time horizonsNot measured69.6%Only GPT-5 measured
Remote Labor IndexNot measured1.7%Only GPT-5 measured
GDPval23.3%34.8%GPT-5
BALROGNot measured32.8%Only GPT-5 measured
DeepResearch Bench41.5%49.6%GPT-5
Vending-Bench 2$574Not measuredOnly Gemini 2.5 Pro measured
BrowseComp-Plus29.5%80.0%GPT-5
Neither model has a result on the other 32 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index56
Reasoning benchmarks for Gemini 2.5 Pro and GPT-5
BenchmarkGemini 2.5 ProGPT-5Leader
GPQA DiamondNot measured85.6%Only GPT-5 measured
MMMU Pro (Vals AI)Not measured81.5%Only GPT-5 measured
GPQA Diamond (Artificial Analysis run)84.4%85.4%GPT-5
Humanity's Last Exam (Artificial Analysis run)22.5%28.5%GPT-5
GPQA Diamond (Epoch AI run)85.3%86.2%GPT-5
ARC-AGI41.0%65.7%GPT-5
ARC-AGI-24.9%9.9%GPT-5
SimpleBenchNot measured56.7%Only GPT-5 measured
Chess puzzlesNot measured36.0%Only GPT-5 measured
Mystery game puzzlesNot measured23.0%Only GPT-5 measured
EBR-benchNot measured12.7%Only GPT-5 measured
VPCTNot measured66.0%Only GPT-5 measured
LMArena Text: hard prompts14551415Gemini 2.5 Pro
LMArena Text: expert14521419Gemini 2.5 Pro
LMArena Text: hard prompts in English14531419Gemini 2.5 Pro
LMArena Vision: diagrams12741252Gemini 2.5 Pro
LMArena Vision: homework12811278Gemini 2.5 Pro
Kagi LLM Benchmark70.3%72.7%GPT-5
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index25
Math benchmarks for Gemini 2.5 Pro and GPT-5
BenchmarkGemini 2.5 ProGPT-5Leader
AIMENot measured93.4%Only GPT-5 measured
MATH 500 (Vals AI)Not measured96.0%Only GPT-5 measured
MGSM (Vals AI)Not measured92.8%Only GPT-5 measured
AA Math Index87.794.3GPT-5
AIME 2025 (Artificial Analysis run)87.7%94.3%GPT-5
OTIS Mock AIME84.7%91.4%GPT-5
FrontierMath, tiers 1 to 324.6%55.4%GPT-5
FrontierMath, tier 40.0%22.0%GPT-5
ProofBenchNot measured18.0%Only GPT-5 measured
MATH level 5Not measured98.1%Only GPT-5 measured
LMArena Text: math14501407Gemini 2.5 Pro
LMArena Text: mathematical work14541405Gemini 2.5 Pro
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index73
Knowledge benchmarks for Gemini 2.5 Pro and GPT-5
BenchmarkGemini 2.5 ProGPT-5Leader
MMLU ProNot measured86.5%Only GPT-5 measured
LegalBench (Vals AI)Not measured86.0%Only GPT-5 measured
CaseLaw (Vals AI)63.9%66.5%GPT-5
CorpFin (Vals AI)60.8%61.1%GPT-5
TaxEval (Vals AI)Not measured73.4%Only GPT-5 measured
MortgageTax (Vals AI)68.9%65.5%Gemini 2.5 Pro
MedQA (Vals AI)Not measured96.3%Only GPT-5 measured
MedCode (Vals AI)50.6%49.6%Gemini 2.5 Pro
MMLU Pro (Artificial Analysis run)86.2%87.1%GPT-5
SimpleQA VerifiedNot measured50.1%Only GPT-5 measured
GeoBenchNot measured81.0%Only GPT-5 measured
LMArena Text: science14801416Gemini 2.5 Pro
LMArena Text: medicine and healthcare14761413Gemini 2.5 Pro
LMArena Text: legal and government14801431Gemini 2.5 Pro
LMArena Text: business and finance14391400Gemini 2.5 Pro
FACTS Benchmark Suite61.5%56.5%Gemini 2.5 Pro
Neither model has a result on the other 2 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index14
Web design benchmarks for Gemini 2.5 Pro and GPT-5
BenchmarkGemini 2.5 ProGPT-5Leader
Design Arena: websites11671184GPT-5
Design Arena: UI components11401180GPT-5
Design Arena: game dev11111185GPT-5
Design Arena: data viz12211221Tie
Design Arena: 3D10811056Gemini 2.5 Pro
Design Arena: all code categories11521168GPT-5
Design Arena: SVGNot measured1189Only GPT-5 measured
Design Arena: ASCII artNot measured1141Only GPT-5 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index257
General benchmarks for Gemini 2.5 Pro and GPT-5
BenchmarkGemini 2.5 ProGPT-5Leader
SAGE (Vals AI)41.9%43.7%GPT-5
MedScribe (Vals AI)73.5%83.7%GPT-5
IFBench48.7%73.1%GPT-5
Long context reasoning (AA-LCR)69.0%78.2%GPT-5
DTBench82.4%90.7%GPT-5
LMCA34.8%40.0%GPT-5
Fiction.LiveBenchNot measured97.2%Only GPT-5 measured
Creative writing (Lech Mazur)83.8%86.0%GPT-5
LMArena Text14581406Gemini 2.5 Pro
LMArena Text: instruction following14371388Gemini 2.5 Pro
LMArena Text: creative writing14541365Gemini 2.5 Pro
LMArena Vision12631232Gemini 2.5 Pro
LMArena Text: English14581409Gemini 2.5 Pro
LMArena Text: non-English14521397Gemini 2.5 Pro
LMArena Text: Chinese15071422Gemini 2.5 Pro
LMArena Text: German14871416Gemini 2.5 Pro
LMArena Text: Japanese14611409Gemini 2.5 Pro
LMArena Text: Korean14341360Gemini 2.5 Pro
LMArena Text: French14731409Gemini 2.5 Pro
LMArena Text: Spanish14741399Gemini 2.5 Pro
LMArena Text: Russian14611407Gemini 2.5 Pro
LMArena Text: Polish14791431Gemini 2.5 Pro
LMArena Text: multi-turn14531426Gemini 2.5 Pro
LMArena Text: longer queries14491399Gemini 2.5 Pro
LMArena Text: writing and language14541384Gemini 2.5 Pro
LMArena Text: entertainment and media14411379Gemini 2.5 Pro
LMArena Vision: English12611231Gemini 2.5 Pro
LMArena Vision: Chinese13001267Gemini 2.5 Pro
LMArena Vision: reading text12701246Gemini 2.5 Pro
LMArena Vision: humor12621219Gemini 2.5 Pro
LMArena Vision: captioning13041212Gemini 2.5 Pro
LMArena Vision: recognizing things12831263Gemini 2.5 Pro
LMArena Vision: creative writing12651210Gemini 2.5 Pro
LMArena Document1421Not measuredOnly Gemini 2.5 Pro measured
Neither model has a result on the other 12 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemini 2.5 Pro and GPT-5
BenchmarkGemini 2.5 ProGPT-5Leader
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 Pro$0.0063Fits in one request
GPT-5$0.0063Fits in one request

Same cost

Repository review

50K input + 3K output tokens

Gemini 2.5 Pro$0.092Fits in one request
GPT-5$0.092Fits in one request

Same cost

Agent loop

200K input + 10K output tokens

Gemini 2.5 Pro$0.350Fits in one request
GPT-5$0.350Fits in one request

Same cost

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 Pro and GPT-5
SpecificationGoogle Gemini 2.5 ProOpenAI GPT-5
MakerGoogleOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedJune 17, 2025August 7, 2025
Context window1.05M400K
Input $/Mtok$1.25$1.25
Output $/Mtok$10.00$10.00
Coding index19.138.8
Independent measurements behind it33
Cost per solved task$0.64$0.39
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemini 2.5 Pro better than GPT-5 for coding?

Pick GPT-5 for coding: it scores 38.8 on the Vibe Coding Index against 19.1 for Gemini 2.5 Pro. Pick Gemini 2.5 Pro for a larger context window (1.05M against 400K tokens) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.

Which is cheaper, Gemini 2.5 Pro or GPT-5?

Gemini 2.5 Pro costs $1.25 per million input tokens and $10.00 per million output tokens; GPT-5 costs $1.25 and $10.00. Per solved SWE-bench Verified task, Gemini 2.5 Pro costs $0.64 and GPT-5 $0.39.

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

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

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

85 benchmarks have a result for both models as of October 21, 2026. Gemini 2.5 Pro's coding index rests on 3 independent benchmarks and GPT-5's on 3. 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-2-5-pro-vs-gpt-5" title="Gemini 2.5 Pro vs GPT-5, 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-2-5-pro-vs-gpt-5">LLMBenchmark.ai, Gemini 2.5 Pro vs GPT-5</a></p>