Enter opens the highlighted result. Esc closes.

Gemini 2.5 Pro vs o3

o3 leads Gemini 2.5 Pro on the Artificial Analysis Intelligence Index, 20.2 to 16.1, and o3 costs 1.3x less per output token ($8.00 vs $10.00 per million). Updated October 21, 2026; 76 benchmarks have a result for both.

Replace Gemini 2.5 Pro Replace o3
Gemini 2.5 ProGoogle
Coding
19.1
Overall
41.8
Output $/M
$10.00
55
o3OpenAI
Coding
No data
Overall
51.1
Output $/M
$8.00
21
vs boards won of 76 shared

Gemini 2.5 Pro or o3: which to pick

Only Gemini 2.5 Pro has a coding score, 19.1 on the Vibe Coding Index; o3 has none, so the two cannot be ranked on coding.

Pick o3 for output tokens 1.3x cheaper ($8.00 vs $10.00 per million) and a lower cost per solved task ($0.571 against $0.64).

Model AGemini 2.5 ProGoogle19.1/1003 independent benchmarks$0.64 per solved taskModel Bo3OpenAINot benchmarkedNo coding benchmark$0.571 per solved task
Shared results
76
Gemini 2.5 Pro only
14
o3 only
26
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, o3 not benchmarked.
Widest category
Agentic work, 18.5 points apart on average over 4 shared benchmarks.
Widest single gap
BrowseComp-Plus: Gemini 2.5 Pro 29.5% against o3 65.9%, 36.4 points apart on a 0 to 100 scale.
Output price
Gemini 2.5 Pro $10.00 against o3 $8.00 per million output tokens, 1.3x apart.
Context window
Gemini 2.5 Pro takes 1.05M tokens, o3 200K.

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 ProBarso3Ties
Coding34
Intelligence02
Agentic work04
Reasoning92
Math33
Knowledge90
Web design50
General266
All shared boards5521
CodingLike-for-likeSix of these boards feed the Vibe Coding Index34
Coding benchmarks for Gemini 2.5 Pro and o3
BenchmarkGemini 2.5 Proo3Leader
Aider polyglotNot measured81.3%Only o3 measured
SWE-bench Verified53.6%58.4%o3
SWE-bench MultimodalNot measured36.0%Only o3 measured
LMArena WebDev1226Not measuredOnly Gemini 2.5 Pro measured
AA Coding Index33.3Not measuredOnly Gemini 2.5 Pro measured
LiveCodeBench (Vals AI)Not measured83.9%Only o3 measured
SWE-bench Verified (Vals AI)54.4%Not measuredOnly Gemini 2.5 Pro measured
Vibe Code Bench (Vals AI)0.4%Not measuredOnly Gemini 2.5 Pro measured
LiveCodeBench (Artificial Analysis run)80.1%80.8%o3
SciCode46.3%Not measuredOnly Gemini 2.5 Pro measured
Terminal-Bench Hard (Artificial Analysis run)26.5%37.1%o3
Terminal-Bench32.6%Not measuredOnly Gemini 2.5 Pro measured
GSO-Bench3.9%8.8%o3
WeirdML54.0%52.4%Gemini 2.5 Pro
ALE-BenchNot measured933.5Only o3 measured
LMArena Text: coding14521407Gemini 2.5 Pro
LMArena Text: software and IT14591415Gemini 2.5 Pro
LMArena WebDev: HTML1235Not measuredOnly Gemini 2.5 Pro measured
LMArena WebDev: from an image1285Not measuredOnly Gemini 2.5 Pro measured
SciCodeNot measured9.2%Only o3 measured
Neither model has a result on the other 19 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Gemini 2.5 Pro and o3
BenchmarkGemini 2.5 Proo3Leader
AA Intelligence Index16.120.2o3
Epoch Capabilities Index145.1146.7o3
Agentic workLike-for-likePublic boards, shown as published, kept out of the index04
Agentic work benchmarks for Gemini 2.5 Pro and o3
BenchmarkGemini 2.5 Proo3Leader
AA Agentic Index1.6Not measuredOnly Gemini 2.5 Pro measured
τ²-Bench Telecom54.1%80.7%o3
METR time horizonsNot measured65.4%Only o3 measured
GDPval23.3%30.8%o3
DeepResearch Bench41.5%45.2%o3
OSWorldNot measured23.0%Only o3 measured
Vending-Bench 2$574Not measuredOnly Gemini 2.5 Pro measured
Berkeley Function Calling Leaderboard (BFCL)Not measured63.0%Only o3 measured
BrowseComp-Plus29.5%65.9%o3
Neither model has a result on the other 32 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index92
Reasoning benchmarks for Gemini 2.5 Pro and o3
BenchmarkGemini 2.5 Proo3Leader
GPQA DiamondNot measured84.1%Only o3 measured
MMMU Pro (Vals AI)Not measured80.4%Only o3 measured
GPQA Diamond (Artificial Analysis run)84.4%82.7%Gemini 2.5 Pro
Humanity's Last Exam (Artificial Analysis run)22.5%20.1%Gemini 2.5 Pro
GPQA Diamond (Epoch AI run)85.3%81.8%Gemini 2.5 Pro
ARC-AGI41.0%60.8%o3
ARC-AGI-24.9%6.5%o3
SimpleBenchNot measured53.1%Only o3 measured
Chess puzzlesNot measured37.0%Only o3 measured
Mystery game puzzlesNot measured29.0%Only o3 measured
VPCTNot measured52.0%Only o3 measured
LMArena Text: hard prompts14551402Gemini 2.5 Pro
LMArena Text: expert14521402Gemini 2.5 Pro
LMArena Text: hard prompts in English14531411Gemini 2.5 Pro
LMArena Vision: diagrams12741220Gemini 2.5 Pro
LMArena Vision: homework12811234Gemini 2.5 Pro
Kagi LLM Benchmark70.3%67.6%Gemini 2.5 Pro
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index33
Math benchmarks for Gemini 2.5 Pro and o3
BenchmarkGemini 2.5 Proo3Leader
AIMENot measured85.3%Only o3 measured
MATH 500 (Vals AI)Not measured94.6%Only o3 measured
MGSM (Vals AI)Not measured91.8%Only o3 measured
AA Math Index87.788.3o3
AIME 2025 (Artificial Analysis run)87.7%88.3%o3
OTIS Mock AIME84.7%84.4%Gemini 2.5 Pro
FrontierMath, tiers 1 to 324.6%33.3%o3
FrontierMath, tier 40.0%Not measuredOnly Gemini 2.5 Pro measured
MATH level 5Not measured97.8%Only o3 measured
LMArena Text: math14501426Gemini 2.5 Pro
LMArena Text: mathematical work14541423Gemini 2.5 Pro
Neither model has a result on the other 2 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index90
Knowledge benchmarks for Gemini 2.5 Pro and o3
BenchmarkGemini 2.5 Proo3Leader
MMLU ProNot measured85.6%Only o3 measured
LegalBench (Vals AI)Not measured83.8%Only o3 measured
CaseLaw (Vals AI)63.9%Not measuredOnly Gemini 2.5 Pro measured
CorpFin (Vals AI)60.8%59.7%Gemini 2.5 Pro
TaxEval (Vals AI)Not measured74.6%Only o3 measured
MortgageTax (Vals AI)68.9%65.7%Gemini 2.5 Pro
MedQA (Vals AI)Not measured96.1%Only o3 measured
MedCode (Vals AI)50.6%47.3%Gemini 2.5 Pro
MMLU Pro (Artificial Analysis run)86.2%85.3%Gemini 2.5 Pro
SimpleQA VerifiedNot measured49.4%Only o3 measured
GeoBenchNot measured74.0%Only o3 measured
LMArena Text: science14801429Gemini 2.5 Pro
LMArena Text: medicine and healthcare14761448Gemini 2.5 Pro
LMArena Text: legal and government14801428Gemini 2.5 Pro
LMArena Text: business and finance14391393Gemini 2.5 Pro
FACTS Benchmark Suite61.5%44.4%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 index50
Web design benchmarks for Gemini 2.5 Pro and o3
BenchmarkGemini 2.5 Proo3Leader
Design Arena: websites11671036Gemini 2.5 Pro
Design Arena: UI components11401017Gemini 2.5 Pro
Design Arena: game dev11111034Gemini 2.5 Pro
Design Arena: data viz12211200Gemini 2.5 Pro
Design Arena: 3D1081Not measuredOnly Gemini 2.5 Pro measured
Design Arena: all code categories11521020Gemini 2.5 Pro
Neither model has a result on the other 3 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index266
General benchmarks for Gemini 2.5 Pro and o3
BenchmarkGemini 2.5 Proo3Leader
SAGE (Vals AI)41.9%41.8%Gemini 2.5 Pro
MedScribe (Vals AI)73.5%76.7%o3
IFBench48.7%71.4%o3
Long context reasoning (AA-LCR)69.0%74.7%o3
DTBench82.4%84.8%o3
LMCA34.8%39.7%o3
Fiction.LiveBenchNot measured88.9%Only o3 measured
Creative writing (Lech Mazur)83.8%83.9%o3
CL-benchNot measured17.8%Only o3 measured
LMArena Text14581410Gemini 2.5 Pro
LMArena Text: instruction following14371368Gemini 2.5 Pro
LMArena Text: creative writing14541359Gemini 2.5 Pro
LMArena Vision12631214Gemini 2.5 Pro
LMArena Text: English14581417Gemini 2.5 Pro
LMArena Text: non-English14521401Gemini 2.5 Pro
LMArena Text: Chinese15071437Gemini 2.5 Pro
LMArena Text: German14871420Gemini 2.5 Pro
LMArena Text: Japanese14611403Gemini 2.5 Pro
LMArena Text: Korean14341370Gemini 2.5 Pro
LMArena Text: French14731430Gemini 2.5 Pro
LMArena Text: Spanish14741395Gemini 2.5 Pro
LMArena Text: Russian14611406Gemini 2.5 Pro
LMArena Text: Polish14791438Gemini 2.5 Pro
LMArena Text: multi-turn14531405Gemini 2.5 Pro
LMArena Text: longer queries14491372Gemini 2.5 Pro
LMArena Text: writing and language14541372Gemini 2.5 Pro
LMArena Text: entertainment and media14411373Gemini 2.5 Pro
LMArena Vision: English12611221Gemini 2.5 Pro
LMArena Vision: Chinese13001237Gemini 2.5 Pro
LMArena Vision: reading text12701218Gemini 2.5 Pro
LMArena Vision: humor12621222Gemini 2.5 Pro
LMArena Vision: captioning13041210Gemini 2.5 Pro
LMArena Vision: recognizing things12831234Gemini 2.5 Pro
LMArena Vision: creative writing12651201Gemini 2.5 Pro
LMArena Document1421Not measuredOnly Gemini 2.5 Pro measured
Neither model has a result on the other 11 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 o3
BenchmarkGemini 2.5 Proo3Leader
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
o3$0.0060Fits in one request

o3 costs less

Repository review

50K input + 3K output tokens

Gemini 2.5 Pro$0.092Fits in one request
o3$0.124Fits in one request

Gemini 2.5 Pro costs less

Agent loop

200K input + 10K output tokens

Gemini 2.5 Pro$0.350Fits in one request
o3$0.480Exceeds the context window

Gemini 2.5 Pro 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 Pro and o3
SpecificationGoogle Gemini 2.5 ProOpenAI o3
MakerGoogleOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedJune 17, 2025April 16, 2025
Context window1.05M200K
Input $/Mtok$1.25$2.00
Output $/Mtok$10.00$8.00
Coding index19.1Not benchmarked
Independent measurements behind it30
Cost per solved task$0.64$0.571
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemini 2.5 Pro better than o3 for coding?

Only Gemini 2.5 Pro has a coding score, 19.1 on the Vibe Coding Index; o3 has none, so the two cannot be ranked on coding. Pick o3 for output tokens 1.3x cheaper ($8.00 vs $10.00 per million) and a lower cost per solved task ($0.571 against $0.64).

Which is cheaper, Gemini 2.5 Pro or o3?

Gemini 2.5 Pro costs $1.25 per million input tokens and $10.00 per million output tokens; o3 costs $2.00 and $8.00. Per solved SWE-bench Verified task, Gemini 2.5 Pro costs $0.64 and o3 $0.571.

Which has the bigger context window, Gemini 2.5 Pro or o3?

Gemini 2.5 Pro, with 1.05M tokens against 200K.

How many benchmarks is the Gemini 2.5 Pro vs o3 comparison based on?

76 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 o3's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next