Comparing 2 models

Claude Sonnet 5.5 vs Gemini 3.6 Flash

Benchmarks through

Verdict

Gemini 3.6 Flash places higher on 1 of the 1 tasks where both are ranked. Gemini 3.6 Flash costs 2.7x less per input token. Gemini 3.6 Flash accepts 1.0x more context.

  • Choose Gemini 3.6 Flash for RAG & Long Context (#7).

Built from the published task rankings below; ranks come from each task's own weighted benchmarks, so a win on one task says nothing about another.

metric
Model 1Claude Sonnet 5.5
Model 2Gemini 3.6 Flash
Best for
Code Completion (#1)
Business Writing (#7)
Provider
anthropic
google
Context
1M
1.0MBest
Input / 1M
$2
$0.75Best
Output / 1M
$10
$3.75Best
Tool use
yesBest
yesBest
Vision
yesBest
yesBest
Reasoning
yesBest
yesBest
Open-weight
—
—
Released
Sep 28, 2026
Jul 21, 2026

Measured head to head

Benchmarks both models were run on

EvaluationClaude Sonnet 5.5Gemini 3.6 FlashSource
Design Arena Coding1345 Elo1279 Elosource · 2026-11-15
Design Arena UI1389 Elo1289 Elosource · 2026-11-15
Design Arena Web-app Agent1295 Elo1174 Elosource · 2026-11-15
Design Arena Website1309 Elo1292 Elosource · 2026-11-15
FACTS Grounding62.5%66.6%source · 2026-11-12
FrontierMath Tiers 1-3 (Epoch AI)88.8% ± 1.958.9% ± 2.9source · 2026-09-29
GPQA Diamond (Epoch AI)95.6% ± 1.494.1% ± 1.4source · 2026-09-29
LiveBench Agentic Coding56.3%43.4%source · 2026-10-18
LiveBench Coding91.4%77.9%source · 2026-10-18
LiveBench Data Analysis59.5%63%source · 2026-10-18
LiveBench Instruction Following56.8%75.4%source · 2026-10-18
LiveBench Language78.0%83.9%source · 2026-10-18
LiveBench Math96.1%86.4%source · 2026-10-18
LiveBench Reasoning91.6%85.2%source · 2026-10-18
LMArena Agent Bash Recovery15-18.2source · 2026-10-08
LMArena Creative Writing1466 Elo1466 Elosource · 2026-11-11
LMArena Instruction Following1487 Elo1467 Elosource · 2026-11-11
LMArena Long Query1487 Elo1475 Elosource · 2026-11-11
LMArena Math1483 Elo1505 Elosource · 2026-11-11
LMArena Text Factuality1472 Elo1472 Elosource · 2026-11-11
LMArena Vision1263 Elo1280 Elosource · 2026-11-09
LMArena Vision Diagrams1308 Elo1312 Elosource · 2026-11-09
LMArena Vision OCR1281 Elo1298 Elosource · 2026-11-09
LMArena WebDev Image-to-Web1744 Elo1545 Elosource · 2026-11-10
OTIS Mock AIME (Epoch AI)100% ± 094.2% ± 3.1source · 2026-09-29
SimpleQA Verified (Epoch AI)46.5% ± 1.666.2% ± 1.5source · 2026-09-29

Values are as published by each evaluator, in its own units; rows from different evaluators are not on a common scale.