Enter opens the highlighted result. Esc closes.

Claude Fable 5 vs Gemini 3.1 Pro Preview

Updated October 21, 2026. 113 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Fable 5 Replace Gemini 3.1 Pro Preview
Claude Fable 5Anthropic
Coding
82.1
Overall
49.6
Output $/M
$50.00
102
Gemini 3.1 Pro PreviewGoogle
Coding
35.3
Overall
29.7
Output $/M
$12.00
11
vs boards won of 113 shared

Decision reading

Pick Claude Fable 5 for coding: it scores 82.1 on the Vibe Coding Index against 35.3 for Gemini 3.1 Pro Preview.

Pick Gemini 3.1 Pro Preview when output tokens cost 4.2x less, or when a solved task costs $0.99 against $2.16.

Model AClaude Fable 5Anthropic82.1/1002 independent benchmarks$2.16 per solved taskModel BGemini 3.1 Pro PreviewGoogle35.3/1001 independent benchmark$0.99 per solved task
Shared results
113
Claude Fable 5 only
13
Gemini 3.1 Pro Preview only
18
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 Fable 5 82.1 from 2 benchmarks, Gemini 3.1 Pro Preview 35.3 from 1 benchmark.
Widest category
Math, 29.2 points apart on average over 6 shared benchmarks.
Widest single gap
ProofBench: Claude Fable 5 95.0% against Gemini 3.1 Pro Preview 26.0%, 69.0 points apart on a 0 to 100 scale.
Output price
Claude Fable 5 $50.00 against Gemini 3.1 Pro Preview $12.00 per million output tokens, 4.2x apart.
Context window
Claude Fable 5 takes 1M tokens, Gemini 3.1 Pro Preview 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 Fable 5BarsGemini 3.1 Pro PreviewTies
Coding200
Intelligence10
Agentic work180
Reasoning124
Math60
Knowledge74
Web design80
General303
All shared boards10211
CodingLike-for-likeFour of these boards feed the Vibe Coding Index200
Coding benchmarks for Claude Fable 5 and Gemini 3.1 Pro Preview
BenchmarkClaude Fable 5Gemini 3.1 Pro PreviewLeader
LiveBench coding98.3%Not measuredOnly Claude Fable 5 measured
LMArena WebDev16241447Claude Fable 5
AA Coding Index76.568.8Claude Fable 5
LiveCodeBench (Vals AI)89.8%88.5%Claude Fable 5
SWE-bench Verified (Vals AI)95.0%78.8%Claude Fable 5
Terminal-Bench 4 (Vals AI)41.4%2.5%Claude Fable 5
Vibe Code Bench (Vals AI)90.3%32.0%Claude Fable 5
Code migration (Vals AI)55.1%17.3%Claude Fable 5
ProgramBench (Vals AI)2.0%0.0%Claude Fable 5
IOI (Vals AI)Not measured51.8%Only Gemini 3.1 Pro Preview measured
Terminal-Bench 2.1 (Vals AI)80.5%70.8%Claude Fable 5
Vibe Code Bench 1-100 (Vals AI)Not measured6.7%Only Gemini 3.1 Pro Preview measured
SciCode61.0%58.7%Claude Fable 5
Terminal-Bench Hard (Artificial Analysis run)62.9%53.8%Claude Fable 5
Terminal-BenchNot measured80.2%Only Gemini 3.1 Pro Preview measured
FrontierCode53.5%Not measuredOnly Claude Fable 5 measured
FrontierSWE47.0%Not measuredOnly Claude Fable 5 measured
GSO-Bench78.4%22.6%Claude Fable 5
WeirdML91.9%72.1%Claude Fable 5
MirrorCode63.9%8.9%Claude Fable 5
ALE-Bench2041.31160.6Claude Fable 5
LMArena Text: coding15181484Claude Fable 5
LMArena Text: software and IT15131487Claude Fable 5
LMArena WebDev: React16311438Claude Fable 5
LMArena WebDev: HTML16511490Claude Fable 5
LMArena WebDev: from an image16231481Claude Fable 5
Neither model has a result on the other 12 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for Claude Fable 5 and Gemini 3.1 Pro Preview
BenchmarkClaude Fable 5Gemini 3.1 Pro PreviewLeader
AA Intelligence Index49.629.7Claude Fable 5
Epoch Capabilities Index163.4Not measuredOnly Claude Fable 5 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index180
Agentic work benchmarks for Claude Fable 5 and Gemini 3.1 Pro Preview
BenchmarkClaude Fable 5Gemini 3.1 Pro PreviewLeader
AA Agentic Index50.78.2Claude Fable 5
Design Arena: agents building web apps12611125Claude Fable 5
Design Arena: agents building full-stack apps12801068Claude Fable 5
Design Arena: agents building mobile apps12641094Claude Fable 5
Design Arena: agents building Android apps12891055Claude Fable 5
Design Arena: agents building Godot games12921236Claude Fable 5
Design Arena: agents building games12851114Claude Fable 5
Design Arena: HTML slides12771153Claude Fable 5
Design Arena: PowerPoint slides12951064Claude Fable 5
LiveBench research86.9%Not measuredOnly Claude Fable 5 measured
LiveBench browser92.0%Not measuredOnly Claude Fable 5 measured
LiveBench long agentic53.2%Not measuredOnly Claude Fable 5 measured
SREBench (Vals AI)Not measured0.0%Only Gemini 3.1 Pro Preview measured
Finance Agent (Vals AI)56.3%43.0%Claude Fable 5
Tax Agent Bench (Vals AI)38.3%9.3%Claude Fable 5
Legal Research Bench (Vals AI)49.5%20.7%Claude Fable 5
Excel Modeling Benchmark (Vals AI)73.7%52.6%Claude Fable 5
BioMysteryBench (Vals AI)Not measured60.0%Only Gemini 3.1 Pro Preview measured
Terminal-Bench-Science (Vals AI)15.7%1.4%Claude Fable 5
Vals Science IndexNot measured27.4%Only Gemini 3.1 Pro Preview measured
τ²-Bench Telecom98.5%95.6%Claude Fable 5
APEX-Agents63.6%35.1%Claude Fable 5
METR time horizonsNot measured77.0%Only Gemini 3.1 Pro Preview measured
Remote Labor Index16.1%Not measuredOnly Claude Fable 5 measured
BALROGNot measured57.0%Only Gemini 3.1 Pro Preview measured
DeepResearch BenchNot measured47.8%Only Gemini 3.1 Pro Preview measured
PostTrainBench41.8%22.0%Claude Fable 5
Vending-Bench 2$5,680$911Claude Fable 5
LMArena Search1229Not measuredOnly Claude Fable 5 measured
Neither model has a result on the other 10 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index124
Reasoning benchmarks for Claude Fable 5 and Gemini 3.1 Pro Preview
BenchmarkClaude Fable 5Gemini 3.1 Pro PreviewLeader
GPQA Diamond93.2%95.5%Gemini 3.1 Pro Preview
LiveBench reasoning89.7%Not measuredOnly Claude Fable 5 measured
MysteryMechanism (Vals AI)Not measured20.7%Only Gemini 3.1 Pro Preview measured
MMMU Pro (Vals AI)89.3%88.2%Claude Fable 5
GPQA Diamond (Artificial Analysis run)92.6%94.1%Gemini 3.1 Pro Preview
Humanity's Last Exam (Artificial Analysis run)55.5%47.0%Claude Fable 5
GPQA Diamond (Epoch AI run)85.9%94.4%Gemini 3.1 Pro Preview
ARC-AGI98.5%98.0%Claude Fable 5
ARC-AGI-289.2%77.1%Claude Fable 5
SimpleBench81.9%79.6%Claude Fable 5
Chess puzzles47.0%51.0%Gemini 3.1 Pro Preview
Mystery game puzzles52.0%34.0%Claude Fable 5
EBR-bench39.5%14.3%Claude Fable 5
LMArena Text: hard prompts15071485Claude Fable 5
LMArena Text: expert15341483Claude Fable 5
LMArena Text: hard prompts in English15091480Claude Fable 5
LMArena Vision: diagrams13571311Claude Fable 5
LMArena Vision: homework13611316Claude Fable 5
Neither model has a result on the other 3 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index60
Math benchmarks for Claude Fable 5 and Gemini 3.1 Pro Preview
BenchmarkClaude Fable 5Gemini 3.1 Pro PreviewLeader
AIMENot measured98.1%Only Gemini 3.1 Pro Preview measured
OTIS Mock AIME100.0%95.6%Claude Fable 5
FrontierMath, tiers 1 to 387.0%59.6%Claude Fable 5
FrontierMath, tier 490.2%26.8%Claude Fable 5
ProofBench95.0%26.0%Claude Fable 5
LMArena Text: math15161486Claude Fable 5
LMArena Text: mathematical work15151478Claude Fable 5
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index74
Knowledge benchmarks for Claude Fable 5 and Gemini 3.1 Pro Preview
BenchmarkClaude Fable 5Gemini 3.1 Pro PreviewLeader
MMLU Pro91.5%91.0%Claude Fable 5
LegalBench (Vals AI)88.6%87.4%Claude Fable 5
CaseLaw (Vals AI)Not measured64.8%Only Gemini 3.1 Pro Preview measured
CorpFin (Vals AI)71.8%64.5%Claude Fable 5
TaxEval (Vals AI)76.9%72.9%Claude Fable 5
MortgageTax (Vals AI)68.9%69.4%Gemini 3.1 Pro Preview
MedQA (Vals AI)Not measured96.4%Only Gemini 3.1 Pro Preview measured
MedCode (Vals AI)56.1%59.1%Gemini 3.1 Pro Preview
SimpleQA Verified70.7%73.5%Gemini 3.1 Pro Preview
LMArena Text: science15061497Claude Fable 5
LMArena Text: medicine and healthcare14801486Gemini 3.1 Pro Preview
LMArena Text: legal and government14981487Claude Fable 5
LMArena Text: business and finance14801459Claude Fable 5
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index80
Web design benchmarks for Claude Fable 5 and Gemini 3.1 Pro Preview
BenchmarkClaude Fable 5Gemini 3.1 Pro PreviewLeader
Design Arena: websites12961234Claude Fable 5
Design Arena: UI components13181226Claude Fable 5
Design Arena: game dev13361203Claude Fable 5
Design Arena: data viz13041209Claude Fable 5
Design Arena: 3D13191234Claude Fable 5
Design Arena: all code categories13101231Claude Fable 5
Design Arena: SVG13021285Claude Fable 5
Design Arena: ASCII art13281270Claude Fable 5
LiveBench design84.7%Not measuredOnly Claude Fable 5 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index303
General benchmarks for Claude Fable 5 and Gemini 3.1 Pro Preview
BenchmarkClaude Fable 5Gemini 3.1 Pro PreviewLeader
LiveBench data analysis80.5%Not measuredOnly Claude Fable 5 measured
Public Benefits Bench (Vals AI)70.4%53.8%Claude Fable 5
SAGE (Vals AI)51.9%48.7%Claude Fable 5
MedScribe (Vals AI)88.5%76.1%Claude Fable 5
Vals Multimodal Index74.2%56.1%Claude Fable 5
IFBench63.5%77.1%Gemini 3.1 Pro Preview
Long context reasoning (AA-LCR)82.3%82.0%Claude Fable 5
DTBench98.4%97.1%Claude Fable 5
LMCA61.2%53.8%Claude Fable 5
CL-benchNot measured20.8%Only Gemini 3.1 Pro Preview measured
Surface Evolver Bench95.0%Not measuredOnly Claude Fable 5 measured
Furniture assembly35.8%26.7%Claude Fable 5
ExploitBenchNot measured26.1%Only Gemini 3.1 Pro Preview measured
CL-bench LifeNot measured16.9%Only Gemini 3.1 Pro Preview measured
LMArena Text14911480Claude Fable 5
LMArena Text: instruction following15021466Claude Fable 5
LMArena Text: creative writing14941482Claude Fable 5
LMArena Vision13251296Claude Fable 5
LMArena Text: English14981478Claude Fable 5
LMArena Text: non-English14821476Claude Fable 5
LMArena Text: Chinese15431527Claude Fable 5
LMArena Text: German14861490Gemini 3.1 Pro Preview
LMArena Text: Japanese15041491Claude Fable 5
LMArena Text: Korean14871455Claude Fable 5
LMArena Text: French15051487Claude Fable 5
LMArena Text: Spanish14981481Claude Fable 5
LMArena Text: Russian15031497Claude Fable 5
LMArena Text: Polish14941498Gemini 3.1 Pro Preview
LMArena Text: multi-turn15041487Claude Fable 5
LMArena Text: longer queries15101482Claude Fable 5
LMArena Text: writing and language15011481Claude Fable 5
LMArena Text: entertainment and media14821465Claude Fable 5
LMArena Vision: English13231287Claude Fable 5
LMArena Vision: Chinese13731364Claude Fable 5
LMArena Vision: reading text13371304Claude Fable 5
LMArena Vision: humor13411322Claude Fable 5
LMArena Vision: captioningNot measured1345Only Gemini 3.1 Pro Preview measured
LMArena Vision: recognizing thingsNot measured1330Only Gemini 3.1 Pro Preview measured
LMArena Vision: creative writing13381324Claude Fable 5
LMArena Document14961444Claude Fable 5
Neither model has a result on the other 6 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Fable 5 and Gemini 3.1 Pro Preview
BenchmarkClaude Fable 5Gemini 3.1 Pro PreviewLeader
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 Fable 5$0.035Fits in one request
Gemini 3.1 Pro Preview$0.0080Fits in one request

Gemini 3.1 Pro Preview costs less

Repository review

50K input + 3K output tokens

Claude Fable 5$0.650Fits in one request
Gemini 3.1 Pro Preview$0.136Fits in one request

Gemini 3.1 Pro Preview costs less

Agent loop

200K input + 10K output tokens

Claude Fable 5$2.50Fits in one request
Gemini 3.1 Pro Preview$0.520Fits in one request

Gemini 3.1 Pro Preview 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 Fable 5 and Gemini 3.1 Pro Preview
SpecificationAnthropic Claude Fable 5Google Gemini 3.1 Pro Preview
MakerAnthropicGoogle
WeightsNo public weights listedNo public weights listed
ReleasedJune 9, 2026February 19, 2026
Context window1M1.05M
Input $/Mtok$10.00$2.00
Output $/Mtok$50.00$12.00
Coding index82.135.3
Independent measurements behind it21
Cost per solved task$2.16$0.99
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Fable 5 better than Gemini 3.1 Pro Preview for coding?

Pick Claude Fable 5 for coding: it scores 82.1 on the Vibe Coding Index against 35.3 for Gemini 3.1 Pro Preview. Pick Gemini 3.1 Pro Preview when output tokens cost 4.2x less, or when a solved task costs $0.99 against $2.16.

Which is cheaper, Claude Fable 5 or Gemini 3.1 Pro Preview?

Claude Fable 5 costs $10.00 per million input tokens and $50.00 per million output tokens; Gemini 3.1 Pro Preview costs $2.00 and $12.00. Per solved SWE-bench Verified task, Claude Fable 5 costs $2.16 and Gemini 3.1 Pro Preview $0.99.

Which has the bigger context window, Claude Fable 5 or Gemini 3.1 Pro Preview?

Gemini 3.1 Pro Preview, with 1.05M tokens against 1M.

How many benchmarks is the Claude Fable 5 vs Gemini 3.1 Pro Preview comparison based on?

113 benchmarks have a result for both models as of October 21, 2026. Claude Fable 5's coding index rests on 2 independent benchmarks and Gemini 3.1 Pro Preview's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next