Skip to content
Leaderboard / Google

Gemini 3.6 Flash

Google High CLOSED Proprietary
Verdict

Gemini 3.6 Flash is a strong all-rounder: #30 of 406 by SIscope score. Strongest at chat quality, weaker at coding. Mid-range on price.

SIscope score
84
#30 of 406
Human-vote rank
#21
of 419 · score 1480
Price per 1M tokens, blended
$1.5
$0.75 in · $3.75 out
Context window
1M
1,048,576 tokens

Shape

Each spoke is a category, 0 at the centre, 100 at the edge.

CodingAgentsno data yetReasoningMathChatInstructions

Category scores

Percentiles: 90 means better than about 90% of tested models.

Coding79
Agents & toolsNo data yet–
Reasoning & knowledge93
Math81
Chat quality95
Following instructions92

What goes into each category · Compare with DeepSeek V4.1 Flash

Human-vote score over time

Text arena, recent updates.

147514801485Oct 20: 1479.5 (rank #20)Oct 22: 1479.6 (rank #20)Oct 28: 1479.8 (rank #21)Oct 20Oct 28

Coding votes over time

WebDev arena, recent updates.

153015381545Oct 16: 1538.2 (rank #45)Oct 18: 1538.1 (rank #46)Oct 19: 1538.1 (rank #48)Oct 22: 1538 (rank #48)Oct 23: 1538 (rank #49)Oct 27: 1537.3 (rank #50)Oct 28: 1537.5 (rank #51)Oct 16Oct 28

Independent test runs

Run by Epoch AI on the same harness for every model. Bars show the share of questions answered correctly.

GPQA Diamond94%
PhD-level science multiple choice questions
Better than 97% of 333 tested models. Run Aug 2, 2026.
SimpleQA Verified66%
Short factual questions; rewards not making things up
Better than 88% of 100 tested models. Run Aug 27, 2026.
OTIS Mock AIME 2024-2594%
Competition maths problems in the style of AIME
Better than 80% of 313 tested models. Run Aug 2, 2026.
FrontierMath Tiers 1-359%
Very hard, unpublished research-style maths problems
Better than 65% of 122 tested models. Run Aug 2, 2026.

Human-vote arenas

People compare two anonymous answers and pick the better one. Scores work like chess ratings.

ArenaRankScoreRange (95%)VotesUpdated
Text arena
Everyday chat, blind human votes
#21 of 41914801475–148436,028Oct 28, 2026
WebDev arena
Building web apps, blind human votes
#51 of 15215381530–15458,722Oct 28, 2026
Vision arena
Questions about images, blind human votes
#20 of 16712991291–13078,979Oct 19, 2026
Agent arena
Real multi-step agent sessions
Not on this board yet

Source: Arena (formerly LMArena) leaderboard dataset, CC BY 4.0. Fetched Nov 4, 2026.

Price

Input
$0.75
per 1M tokens
Output
$3.75
per 1M tokens
Blended
$1.5
3 in : 1 out, per 1M
Context window
1M
max tokens per request
Speed
Coming soon
our own tests

List price from the OpenRouter models API (google/gemini-3.6-flash), Nov 4, 2026. Providers can charge differently.