LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Claude Sonnet 4.6 vs Gemini 3.5 Flash Lite

Updated October 21, 2026. 77 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Sonnet 4.6 Replace Gemini 3.5 Flash Lite
Claude Sonnet 4.6Anthropic
Coding
57.8
Overall
30.1
Output $/M
$15.00
67
Gemini 3.5 Flash LiteGoogle
Coding
33.6
Overall
22.2
Output $/M
$2.50
9
vs boards won of 77 shared, 1 tied

Decision reading

Pick Claude Sonnet 4.6 for coding: it scores 57.8 on the Vibe Coding Index against 33.6 for Gemini 3.5 Flash Lite.

Pick Gemini 3.5 Flash Lite when output tokens cost 6.0x less, or when a solved task costs $0.41 against $1.68.

Model AClaude Sonnet 4.6Anthropic57.8/1002 independent benchmarks$1.68 per solved taskModel BGemini 3.5 Flash LiteGoogle33.6/1001 independent benchmark$0.41 per solved task
Shared results
77
Claude Sonnet 4.6 only
40
Gemini 3.5 Flash Lite only
6
Like-for-like categories
7 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 Sonnet 4.6 57.8 from 2 benchmarks, Gemini 3.5 Flash Lite 33.6 from 1 benchmark.
Widest category
Agentic work, 15.8 points apart on average over 6 shared benchmarks.
Widest single gap
ARC-AGI-2: Claude Sonnet 4.6 60.4% against Gemini 3.5 Flash Lite 10.3%, 50.1 points apart on a 0 to 100 scale.
Output price
Claude Sonnet 4.6 $15.00 against Gemini 3.5 Flash Lite $2.50 per million output tokens, 6.0x apart.
Context window
Claude Sonnet 4.6 takes 1M tokens, Gemini 3.5 Flash Lite 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 Sonnet 4.6BarsGemini 3.5 Flash LiteTies
Coding140
Intelligence20
Agentic work60
Reasoning1211 tie
Math40
Knowledge72
General226
All shared boards6791 tie
CodingLike-for-likeFour of these boards feed the Vibe Coding Index140
Coding benchmarks for Claude Sonnet 4.6 and Gemini 3.5 Flash Lite
BenchmarkClaude Sonnet 4.6Gemini 3.5 Flash LiteLeader
LiveBench coding66.6%Not measuredOnly Claude Sonnet 4.6 measured
LMArena WebDev15231435Claude Sonnet 4.6
AA Coding Index63.049.3Claude Sonnet 4.6
LiveCodeBench (Vals AI)82.1%79.0%Claude Sonnet 4.6
SWE-bench Verified (Vals AI)77.4%75.0%Claude Sonnet 4.6
Vibe Code Bench (Vals AI)55.8%37.2%Claude Sonnet 4.6
Code migration (Vals AI)39.9%6.2%Claude Sonnet 4.6
ProgramBench (Vals AI)0.5%0.0%Claude Sonnet 4.6
Terminal-Bench 2.1 (Vals AI)57.3%50.2%Claude Sonnet 4.6
SkillsBench (Vals AI)49.0%Not measuredOnly Claude Sonnet 4.6 measured
CyberBench (Vals AI)Not measured59.1%Only Gemini 3.5 Flash Lite measured
SciCode50.1%41.3%Claude Sonnet 4.6
Terminal-Bench Hard (Artificial Analysis run)53.0%Not measuredOnly Claude Sonnet 4.6 measured
Terminal-Bench53.4%Not measuredOnly Claude Sonnet 4.6 measured
FrontierCode24.3%Not measuredOnly Claude Sonnet 4.6 measured
WeirdML66.1%39.0%Claude Sonnet 4.6
ALE-BenchNot measured765.3Only Gemini 3.5 Flash Lite measured
LMArena Text: coding15031453Claude Sonnet 4.6
LMArena Text: software and IT14911451Claude Sonnet 4.6
LMArena WebDev: React15121408Claude Sonnet 4.6
LMArena WebDev: HTML1527Not measuredOnly Claude Sonnet 4.6 measured
LMArena WebDev: from an image15291448Claude Sonnet 4.6
Neither model has a result on the other 16 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Sonnet 4.6 and Gemini 3.5 Flash Lite
BenchmarkClaude Sonnet 4.6Gemini 3.5 Flash LiteLeader
AA Intelligence Index30.122.2Claude Sonnet 4.6
Epoch Capabilities Index152.8144.9Claude Sonnet 4.6
Agentic workLike-for-likePublic boards, shown as published, kept out of the index60
Agentic work benchmarks for Claude Sonnet 4.6 and Gemini 3.5 Flash Lite
BenchmarkClaude Sonnet 4.6Gemini 3.5 Flash LiteLeader
AA Agentic Index31.814.3Claude Sonnet 4.6
Design Arena: agents building web apps1190Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: agents building full-stack apps1213Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: agents building mobile apps1212Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: agents building Android apps1202Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: agents building Godot games1226Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: agents building games1177Not measuredOnly Claude Sonnet 4.6 measured
LiveBench research63.6%Not measuredOnly Claude Sonnet 4.6 measured
LiveBench browser68.0%Not measuredOnly Claude Sonnet 4.6 measured
LiveBench long agentic23.1%Not measuredOnly Claude Sonnet 4.6 measured
Finance Agent (Vals AI)51.0%47.4%Claude Sonnet 4.6
Tax Agent Bench (Vals AI)25.8%7.2%Claude Sonnet 4.6
Legal Research Bench (Vals AI)38.5%13.9%Claude Sonnet 4.6
Excel Modeling Benchmark (Vals AI)60.2%43.2%Claude Sonnet 4.6
τ²-Bench Telecom79.5%Not measuredOnly Claude Sonnet 4.6 measured
APEX-Agents43.0%29.3%Claude Sonnet 4.6
OSWorld 2.09.3%Not measuredOnly Claude Sonnet 4.6 measured
DeepResearch Bench54.9%Not measuredOnly Claude Sonnet 4.6 measured
OSWorld72.1%Not measuredOnly Claude Sonnet 4.6 measured
Vending-Bench 2$7,204Not measuredOnly Claude Sonnet 4.6 measured
Neither model has a result on the other 19 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index121
Reasoning benchmarks for Claude Sonnet 4.6 and Gemini 3.5 Flash Lite
BenchmarkClaude Sonnet 4.6Gemini 3.5 Flash LiteLeader
GPQA Diamond85.6%83.8%Claude Sonnet 4.6
LiveBench reasoning86.4%Not measuredOnly Claude Sonnet 4.6 measured
MMMU Pro (Vals AI)83.6%83.6%Tie
GPQA Diamond (Artificial Analysis run)87.5%83.8%Claude Sonnet 4.6
Humanity's Last Exam (Artificial Analysis run)33.6%18.8%Claude Sonnet 4.6
GPQA Diamond (Epoch AI run)87.4%83.3%Claude Sonnet 4.6
ARC-AGI86.5%53.5%Claude Sonnet 4.6
ARC-AGI-260.4%10.3%Claude Sonnet 4.6
Chess puzzles23.0%21.0%Claude Sonnet 4.6
Mystery game puzzles16.0%19.0%Gemini 3.5 Flash Lite
LMArena Text: hard prompts14851441Claude Sonnet 4.6
LMArena Text: expert15001434Claude Sonnet 4.6
LMArena Text: hard prompts in English14931440Claude Sonnet 4.6
LMArena Vision: diagrams13061284Claude Sonnet 4.6
LMArena Vision: homework13111291Claude Sonnet 4.6
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index40
Math benchmarks for Claude Sonnet 4.6 and Gemini 3.5 Flash Lite
BenchmarkClaude Sonnet 4.6Gemini 3.5 Flash LiteLeader
AIME92.3%Not measuredOnly Claude Sonnet 4.6 measured
OTIS Mock AIME85.8%71.1%Claude Sonnet 4.6
FrontierMath, tiers 1 to 3Not measured26.0%Only Gemini 3.5 Flash Lite measured
FrontierMath, tier 4Not measured0.0%Only Gemini 3.5 Flash Lite measured
ProofBench45.0%13.0%Claude Sonnet 4.6
LMArena Text: math14621434Claude Sonnet 4.6
LMArena Text: mathematical work14831433Claude Sonnet 4.6
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index72
Knowledge benchmarks for Claude Sonnet 4.6 and Gemini 3.5 Flash Lite
BenchmarkClaude Sonnet 4.6Gemini 3.5 Flash LiteLeader
MMLU Pro87.3%85.8%Claude Sonnet 4.6
LegalBench (Vals AI)82.1%84.1%Gemini 3.5 Flash Lite
CaseLaw (Vals AI)64.0%Not measuredOnly Claude Sonnet 4.6 measured
CorpFin (Vals AI)65.3%60.7%Claude Sonnet 4.6
TaxEval (Vals AI)77.1%72.6%Claude Sonnet 4.6
MortgageTax (Vals AI)67.7%68.7%Gemini 3.5 Flash Lite
MedQA (Vals AI)92.1%Not measuredOnly Claude Sonnet 4.6 measured
MedCode (Vals AI)Not measured43.5%Only Gemini 3.5 Flash Lite measured
SimpleQA Verified35.5%Not measuredOnly Claude Sonnet 4.6 measured
LMArena Text: science14741451Claude Sonnet 4.6
LMArena Text: medicine and healthcare14511438Claude Sonnet 4.6
LMArena Text: legal and government14701431Claude Sonnet 4.6
LMArena Text: business and finance14641423Claude Sonnet 4.6
Neither model has a result on the other 4 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Web design benchmarks for Claude Sonnet 4.6 and Gemini 3.5 Flash Lite
BenchmarkClaude Sonnet 4.6Gemini 3.5 Flash LiteLeader
Design Arena: websites1285Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: UI components1271Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: game dev1259Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: data viz1278Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: 3D1234Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: all code categories1276Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: SVG1196Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: ASCII art1235Not measuredOnly Claude Sonnet 4.6 measured
LiveBench design71.8%Not measuredOnly Claude Sonnet 4.6 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index226
General benchmarks for Claude Sonnet 4.6 and Gemini 3.5 Flash Lite
BenchmarkClaude Sonnet 4.6Gemini 3.5 Flash LiteLeader
LiveBench data analysis76.1%Not measuredOnly Claude Sonnet 4.6 measured
Public Benefits Bench (Vals AI)62.5%51.8%Claude Sonnet 4.6
SAGE (Vals AI)46.6%47.3%Gemini 3.5 Flash Lite
MedScribe (Vals AI)Not measured70.9%Only Gemini 3.5 Flash Lite measured
Vals Multimodal Index60.6%Not measuredOnly Claude Sonnet 4.6 measured
IFBench56.6%Not measuredOnly Claude Sonnet 4.6 measured
Long context reasoning (AA-LCR)80.0%76.0%Claude Sonnet 4.6
DTBench89.9%83.5%Claude Sonnet 4.6
LMCA46.5%37.6%Claude Sonnet 4.6
ExploitBench23.6%Not measuredOnly Claude Sonnet 4.6 measured
LMArena Text14581435Claude Sonnet 4.6
LMArena Text: instruction following14761419Claude Sonnet 4.6
LMArena Text: creative writing14351421Claude Sonnet 4.6
LMArena Vision12831269Claude Sonnet 4.6
LMArena Text: English14721438Claude Sonnet 4.6
LMArena Text: non-English14401427Claude Sonnet 4.6
LMArena Text: Chinese14911468Claude Sonnet 4.6
LMArena Text: German14281454Gemini 3.5 Flash Lite
LMArena Text: Japanese14201426Gemini 3.5 Flash Lite
LMArena Text: Korean14101407Claude Sonnet 4.6
LMArena Text: French14651451Claude Sonnet 4.6
LMArena Text: Spanish14641441Claude Sonnet 4.6
LMArena Text: Russian14401443Gemini 3.5 Flash Lite
LMArena Text: Polish14431437Claude Sonnet 4.6
LMArena Text: multi-turn14641445Claude Sonnet 4.6
LMArena Text: longer queries14791435Claude Sonnet 4.6
LMArena Text: writing and language14441428Claude Sonnet 4.6
LMArena Text: entertainment and media14311414Claude Sonnet 4.6
LMArena Vision: English12981269Claude Sonnet 4.6
LMArena Vision: Chinese13071311Gemini 3.5 Flash Lite
LMArena Vision: reading text12961280Claude Sonnet 4.6
LMArena Vision: humor12481287Gemini 3.5 Flash Lite
LMArena Vision: recognizing things1195Not measuredOnly Claude Sonnet 4.6 measured
LMArena Vision: creative writing12721260Claude Sonnet 4.6
LMArena Document1482Not measuredOnly Claude Sonnet 4.6 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 Claude Sonnet 4.6 and Gemini 3.5 Flash Lite
BenchmarkClaude Sonnet 4.6Gemini 3.5 Flash LiteLeader
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 Sonnet 4.6$0.011Fits in one request
Gemini 3.5 Flash Lite$0.0015Fits in one request

Gemini 3.5 Flash Lite costs less

Repository review

50K input + 3K output tokens

Claude Sonnet 4.6$0.195Fits in one request
Gemini 3.5 Flash Lite$0.022Fits in one request

Gemini 3.5 Flash Lite costs less

Agent loop

200K input + 10K output tokens

Claude Sonnet 4.6$0.750Fits in one request
Gemini 3.5 Flash Lite$0.085Fits in one request

Gemini 3.5 Flash Lite 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 Sonnet 4.6 and Gemini 3.5 Flash Lite
SpecificationAnthropic Claude Sonnet 4.6Google Gemini 3.5 Flash Lite
MakerAnthropicGoogle
WeightsNo public weights listedNo public weights listed
ReleasedFebruary 17, 2026July 21, 2026
Context window1M1.05M
Input $/Mtok$3.00$0.30
Output $/Mtok$15.00$2.50
Coding index57.833.6
Independent measurements behind it21
Cost per solved task$1.68$0.41
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Sonnet 4.6 better than Gemini 3.5 Flash Lite for coding?

Pick Claude Sonnet 4.6 for coding: it scores 57.8 on the Vibe Coding Index against 33.6 for Gemini 3.5 Flash Lite. Pick Gemini 3.5 Flash Lite when output tokens cost 6.0x less, or when a solved task costs $0.41 against $1.68.

Which is cheaper, Claude Sonnet 4.6 or Gemini 3.5 Flash Lite?

Claude Sonnet 4.6 costs $3.00 per million input tokens and $15.00 per million output tokens; Gemini 3.5 Flash Lite costs $0.30 and $2.50. Per solved SWE-bench Verified task, Claude Sonnet 4.6 costs $1.68 and Gemini 3.5 Flash Lite $0.41.

Which has the bigger context window, Claude Sonnet 4.6 or Gemini 3.5 Flash Lite?

Gemini 3.5 Flash Lite, with 1.05M tokens against 1M.

How many benchmarks is the Claude Sonnet 4.6 vs Gemini 3.5 Flash Lite comparison based on?

77 benchmarks have a result for both models as of October 21, 2026. Claude Sonnet 4.6's coding index rests on 2 independent benchmarks and Gemini 3.5 Flash Lite's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next