LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Claude Opus 4.1 vs Gemini 2.5 Pro

Updated October 21, 2026. 53 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Opus 4.1 Replace Gemini 2.5 Pro
Claude Opus 4.1Anthropic
Coding
27.2
Overall
22.8
Output $/M
$75.00
17
Gemini 2.5 ProGoogle
Coding
37.0
Overall
16.1
Output $/M
$10.00
36
vs boards won of 53 shared

Decision reading

Pick Gemini 2.5 Pro for coding: it scores 37.0 on the Vibe Coding Index against 27.2 for Claude Opus 4.1.

Pick Claude Opus 4.1 when what matters is LMArena WebDev or Terminal-Bench, where it leads.

Model AClaude Opus 4.1Anthropic27.2/1001 independent benchmarkNo cost per solved taskModel BGemini 2.5 ProGoogle37.0/1002 independent benchmarks$0.64 per solved task
Shared results
53
Claude Opus 4.1 only
18
Gemini 2.5 Pro only
34
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
Claude Opus 4.1 27.2 from 1 benchmark, Gemini 2.5 Pro 37.0 from 2 benchmarks.
Widest category
Agentic work, 13.5 points apart on average over 2 shared benchmarks.
Widest single gap
LMArena WebDev: HTML: Claude Opus 4.1 1399 against Gemini 2.5 Pro 1235, 27.3 points apart on a 0 to 100 scale.
Output price
Claude Opus 4.1 $75.00 against Gemini 2.5 Pro $10.00 per million output tokens, 7.5x apart.
Context window
Claude Opus 4.1 takes 200K tokens, Gemini 2.5 Pro 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
CategoryClaude Opus 4.1BarsGemini 2.5 ProTies
Coding42
Intelligence11
Agentic work20
Reasoning04
Math14
Knowledge06
Web design51
General418
All shared boards1736
CodingLike-for-likeFour of these boards feed the Vibe Coding Index42
Coding benchmarks for Claude Opus 4.1 and Gemini 2.5 Pro
BenchmarkClaude Opus 4.1Gemini 2.5 ProLeader
SWE-bench VerifiedNot measured53.6%Only Gemini 2.5 Pro measured
LMArena WebDev13901226Claude Opus 4.1
AA Coding IndexNot measured33.3Only Gemini 2.5 Pro measured
LiveCodeBench (Vals AI)66.5%Not measuredOnly Claude Opus 4.1 measured
SWE-bench Verified (Vals AI)Not measured54.4%Only Gemini 2.5 Pro measured
Vibe Code Bench (Vals AI)Not measured0.4%Only Gemini 2.5 Pro measured
LiveCodeBench (Artificial Analysis run)Not measured80.1%Only Gemini 2.5 Pro measured
SciCodeNot measured46.3%Only Gemini 2.5 Pro measured
Terminal-Bench Hard (Artificial Analysis run)Not measured26.5%Only Gemini 2.5 Pro measured
Terminal-Bench38.0%32.6%Claude Opus 4.1
GSO-BenchNot measured3.9%Only Gemini 2.5 Pro measured
WeirdML45.9%54.0%Gemini 2.5 Pro
Cybench42.0%Not measuredOnly Claude Opus 4.1 measured
LMArena Text: coding14791452Claude Opus 4.1
LMArena Text: software and IT14561459Gemini 2.5 Pro
LMArena WebDev: HTML13991235Claude Opus 4.1
LMArena WebDev: from an imageNot measured1285Only Gemini 2.5 Pro measured
Neither model has a result on the other 21 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
Intelligence benchmarks for Claude Opus 4.1 and Gemini 2.5 Pro
BenchmarkClaude Opus 4.1Gemini 2.5 ProLeader
AA Intelligence Index22.816.1Claude Opus 4.1
Epoch Capabilities Index144.1145.1Gemini 2.5 Pro
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
Agentic work benchmarks for Claude Opus 4.1 and Gemini 2.5 Pro
BenchmarkClaude Opus 4.1Gemini 2.5 ProLeader
AA Agentic IndexNot measured1.6Only Gemini 2.5 Pro measured
τ²-Bench TelecomNot measured54.1%Only Gemini 2.5 Pro measured
METR time horizons66.8%Not measuredOnly Claude Opus 4.1 measured
GDPval43.6%23.3%Claude Opus 4.1
DeepResearch Bench48.3%41.5%Claude Opus 4.1
Vending-Bench 2Not measured$574Only Gemini 2.5 Pro measured
Neither model has a result on the other 33 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index04
Reasoning benchmarks for Claude Opus 4.1 and Gemini 2.5 Pro
BenchmarkClaude Opus 4.1Gemini 2.5 ProLeader
GPQA Diamond76.3%Not measuredOnly Claude Opus 4.1 measured
MMMU Pro (Vals AI)77.5%Not measuredOnly Claude Opus 4.1 measured
GPQA Diamond (Artificial Analysis run)Not measured84.4%Only Gemini 2.5 Pro measured
Humanity's Last Exam (Artificial Analysis run)Not measured22.5%Only Gemini 2.5 Pro measured
GPQA Diamond (Epoch AI run)77.3%85.3%Gemini 2.5 Pro
ARC-AGINot measured41.0%Only Gemini 2.5 Pro measured
ARC-AGI-2Not measured4.9%Only Gemini 2.5 Pro measured
SimpleBench60.0%Not measuredOnly Claude Opus 4.1 measured
Mystery game puzzles21.0%Not measuredOnly Claude Opus 4.1 measured
EBR-bench7.9%Not measuredOnly Claude Opus 4.1 measured
VPCT35.0%Not measuredOnly Claude Opus 4.1 measured
LMArena Text: hard prompts14421455Gemini 2.5 Pro
LMArena Text: expert14381452Gemini 2.5 Pro
LMArena Text: hard prompts in English14511453Gemini 2.5 Pro
LMArena Vision: diagramsNot measured1274Only Gemini 2.5 Pro measured
LMArena Vision: homeworkNot measured1281Only Gemini 2.5 Pro measured
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index14
Math benchmarks for Claude Opus 4.1 and Gemini 2.5 Pro
BenchmarkClaude Opus 4.1Gemini 2.5 ProLeader
AIME78.2%Not measuredOnly Claude Opus 4.1 measured
MATH 500 (Vals AI)95.4%Not measuredOnly Claude Opus 4.1 measured
MGSM (Vals AI)94.4%Not measuredOnly Claude Opus 4.1 measured
AA Math IndexNot measured87.7Only Gemini 2.5 Pro measured
AIME 2025 (Artificial Analysis run)Not measured87.7%Only Gemini 2.5 Pro measured
OTIS Mock AIME68.9%84.7%Gemini 2.5 Pro
FrontierMath, tiers 1 to 312.6%24.6%Gemini 2.5 Pro
FrontierMath, tier 42.4%0.0%Claude Opus 4.1
LMArena Text: math14311450Gemini 2.5 Pro
LMArena Text: mathematical work14341454Gemini 2.5 Pro
Neither model has a result on the other 3 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index06
Knowledge benchmarks for Claude Opus 4.1 and Gemini 2.5 Pro
BenchmarkClaude Opus 4.1Gemini 2.5 ProLeader
MMLU Pro87.9%Not measuredOnly Claude Opus 4.1 measured
LegalBench (Vals AI)83.5%Not measuredOnly Claude Opus 4.1 measured
CaseLaw (Vals AI)Not measured63.9%Only Gemini 2.5 Pro measured
CorpFin (Vals AI)Not measured60.8%Only Gemini 2.5 Pro measured
TaxEval (Vals AI)73.7%Not measuredOnly Claude Opus 4.1 measured
MortgageTax (Vals AI)61.1%68.9%Gemini 2.5 Pro
MedQA (Vals AI)93.6%Not measuredOnly Claude Opus 4.1 measured
MedCode (Vals AI)47.2%50.6%Gemini 2.5 Pro
MMLU Pro (Artificial Analysis run)Not measured86.2%Only Gemini 2.5 Pro measured
LMArena Text: science14221480Gemini 2.5 Pro
LMArena Text: medicine and healthcare14161476Gemini 2.5 Pro
LMArena Text: legal and government14211480Gemini 2.5 Pro
LMArena Text: business and finance14061439Gemini 2.5 Pro
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index51
Web design benchmarks for Claude Opus 4.1 and Gemini 2.5 Pro
BenchmarkClaude Opus 4.1Gemini 2.5 ProLeader
Design Arena: websites11771167Claude Opus 4.1
Design Arena: UI components11641139Claude Opus 4.1
Design Arena: game dev11721112Claude Opus 4.1
Design Arena: data viz11661222Gemini 2.5 Pro
Design Arena: 3D11531080Claude Opus 4.1
Design Arena: all code categories11711152Claude Opus 4.1
Design Arena: SVG1152Not measuredOnly Claude Opus 4.1 measured
Design Arena: ASCII art1167Not measuredOnly Claude Opus 4.1 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index418
General benchmarks for Claude Opus 4.1 and Gemini 2.5 Pro
BenchmarkClaude Opus 4.1Gemini 2.5 ProLeader
SAGE (Vals AI)31.4%41.9%Gemini 2.5 Pro
MedScribe (Vals AI)73.9%73.5%Claude Opus 4.1
IFBenchNot measured48.7%Only Gemini 2.5 Pro measured
Long context reasoning (AA-LCR)Not measured69.0%Only Gemini 2.5 Pro measured
DTBench80.0%82.4%Gemini 2.5 Pro
LMCA37.1%34.8%Claude Opus 4.1
Creative writing (Lech Mazur)84.7%83.8%Claude Opus 4.1
LMArena Text14191458Gemini 2.5 Pro
LMArena Text: instruction following14351437Gemini 2.5 Pro
LMArena Text: creative writing14121454Gemini 2.5 Pro
LMArena VisionNot measured1263Only Gemini 2.5 Pro measured
LMArena Text: English14331458Gemini 2.5 Pro
LMArena Text: non-English14051452Gemini 2.5 Pro
LMArena Text: Chinese14271507Gemini 2.5 Pro
LMArena Text: German14131487Gemini 2.5 Pro
LMArena Text: Japanese13771461Gemini 2.5 Pro
LMArena Text: Korean13811434Gemini 2.5 Pro
LMArena Text: French14331473Gemini 2.5 Pro
LMArena Text: Spanish14481474Gemini 2.5 Pro
LMArena Text: Russian14221461Gemini 2.5 Pro
LMArena Text: Polish14131479Gemini 2.5 Pro
LMArena Text: multi-turn14441453Gemini 2.5 Pro
LMArena Text: longer queries14551449Claude Opus 4.1
LMArena Text: writing and language14181454Gemini 2.5 Pro
LMArena Text: entertainment and media13981441Gemini 2.5 Pro
LMArena Vision: EnglishNot measured1261Only Gemini 2.5 Pro measured
LMArena Vision: ChineseNot measured1300Only Gemini 2.5 Pro measured
LMArena Vision: reading textNot measured1270Only Gemini 2.5 Pro measured
LMArena Vision: humorNot measured1262Only Gemini 2.5 Pro measured
LMArena Vision: captioningNot measured1304Only Gemini 2.5 Pro measured
LMArena Vision: recognizing thingsNot measured1283Only Gemini 2.5 Pro measured
LMArena Vision: creative writingNot measured1265Only Gemini 2.5 Pro measured
LMArena DocumentNot measured1421Only Gemini 2.5 Pro measured
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 Claude Opus 4.1 and Gemini 2.5 Pro
BenchmarkClaude Opus 4.1Gemini 2.5 ProLeader
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

Claude Opus 4.1$0.052Fits in one request
Gemini 2.5 Pro$0.0063Fits in one request

Gemini 2.5 Pro costs less

Repository review

50K input + 3K output tokens

Claude Opus 4.1$0.975Fits in one request
Gemini 2.5 Pro$0.092Fits in one request

Gemini 2.5 Pro costs less

Agent loop

200K input + 10K output tokens

Claude Opus 4.1$3.75Exceeds the context window
Gemini 2.5 Pro$0.350Fits in one request

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 Claude Opus 4.1 and Gemini 2.5 Pro
SpecificationAnthropic Claude Opus 4.1Google Gemini 2.5 Pro
MakerAnthropicGoogle
WeightsNo public weights listedNo public weights listed
ReleasedAugust 5, 2025June 17, 2025
Context window200K1.05M
Input $/Mtok$15.00$1.25
Output $/Mtok$75.00$10.00
Coding index27.237.0
Independent measurements behind it12
Cost per solved taskNot computable$0.64
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.1 better than Gemini 2.5 Pro for coding?

Pick Gemini 2.5 Pro for coding: it scores 37.0 on the Vibe Coding Index against 27.2 for Claude Opus 4.1. Pick Claude Opus 4.1 when what matters is LMArena WebDev or Terminal-Bench, where it leads.

Which is cheaper, Claude Opus 4.1 or Gemini 2.5 Pro?

Claude Opus 4.1 costs $15.00 per million input tokens and $75.00 per million output tokens; Gemini 2.5 Pro costs $1.25 and $10.00. Cost per solved task is known for Gemini 2.5 Pro only.

Which has the bigger context window, Claude Opus 4.1 or Gemini 2.5 Pro?

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

How many benchmarks is the Claude Opus 4.1 vs Gemini 2.5 Pro comparison based on?

53 benchmarks have a result for both models as of October 21, 2026. Claude Opus 4.1's coding index rests on 1 independent benchmark and Gemini 2.5 Pro's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next