Skip to main content
Launching the open-source gateway

Gemini 3.5 Flash vs Gemini 3.6 Flash

SpecGemini 3.5 FlashGemini 3.6 Flash
Respan Index44.4 (#48)44.4 (#48)
Blended price per 1M$1.69$0.75
Context window1.0M1.0M
Input / output per 1M$0.75 / $4.5$0.375 / $1.88
Max output66K66K
Inputtext, vision, audiotext, vision, audio
Released2026-05-192026-07-21

Respan Index by category

Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.

CategoryGemini 3.5 FlashGemini 3.6 Flash
Coding19.4 Gemini 3.5 Flash18.1 Gemini 3.6 Flash
Agents49.8 Gemini 3.5 Flash57.3 Gemini 3.6 Flash
Reasoning50.1 Gemini 3.5 Flash43.4 Gemini 3.6 Flash
Knowledge & language65.7 Gemini 3.5 Flash65.3 Gemini 3.6 Flash
Human preference53.5 Gemini 3.5 Flash54.5 Gemini 3.6 Flash

How the Respan Index works

Benchmarks both report

Gemini 3.5 Flash leads on 14 of the 25 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkGemini 3.5 FlashGemini 3.6 Flash
Chess Puzzles (Epoch AI)45%42%
LMArena Elo14781483
LMArena WebDev (LMArena)14991538
LMArena Vision (LMArena)12821282
APEX-Agents (Mercor)27.5%46.9%
DeepSWE v1.1 (Datacurve)36.1%46.7%
FrontierMath Tier 4 v2 (Epoch AI)26.8%22%
FrontierMath Tiers 1-3 v2 (Epoch AI)62.8%58.9%
GPQA Diamond92.8%94.1%
LiveBench Agentic Coding (LiveBench)49%43.4%
LiveBench Coding (LiveBench)78.2%77.9%
LiveBench Data Analysis (LiveBench)64.9%63%
LiveBench Instruction Following (LiveBench)75.6%75.4%
LiveBench Language (LiveBench)84.6%83.9%
LiveBench Mathematics (LiveBench)88.2%86.4%
LiveBench Reasoning (LiveBench)82%85.1%
Mystery Game Puzzles (Epoch AI)32%30%
OTIS Mock AIME 2024-2025 (Epoch AI)95.6%94.2%
SAGE (Vals AI)49.9%48.7%
SimpleQA Verified66.2%66.2%
WeirdML (Håvard Tveit Ihle)62.6%56.1%
AIME 202695%96.7%
OSWorld-Verified78.4%83%
SWE-Bench Pro (Public)55.1%58.7%
Terminal-bench 2.176.2%78%

FAQ

Is Gemini 3.5 Flash better than Gemini 3.6 Flash?

Gemini 3.5 Flash and Gemini 3.6 Flash tie on the Respan Index at 44.4. Gemini 3.5 Flash leads on 14 of the 25 benchmarks both report.

Which is cheaper, Gemini 3.5 Flash or Gemini 3.6 Flash?

Gemini 3.5 Flash lists at $0.75 input and $4.5 output per 1M tokens; Gemini 3.6 Flash at $0.375 and $1.88. Gemini 3.6 Flash is 2.3x cheaper per token at list price.

Which has the larger context window?

Both accept 1.0M tokens of context.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.

Start for freeGet a demo