Skip to content
Leaderboard / Google

Gemini 3.7 Flash

Google High CLOSED Proprietary
Verdict

Gemini 3.7 Flash is a strong all-rounder: #50 of 406 by SIscope score. Strongest at chat quality, weaker at agents & tools. Mid-range on price.

SIscope score
79
#50 of 406
Human-vote rank
#15
of 419 · score 1489
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.

CodingAgentsReasoningMathChatInstructions

Category scores

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

Coding86
Agents & tools43
Reasoning & knowledge95
Math88
Chat quality97
Following instructions96

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

Human-vote score over time

Text arena, recent updates.

148014881495Oct 15: 1487.3 (rank #14)Oct 20: 1488.5 (rank #14)Oct 22: 1489.5 (rank #14)Oct 28: 1489.1 (rank #15)Oct 15Oct 28

Coding votes over time

WebDev arena, recent updates.

158515931600Oct 16: 1590.6 (rank #30)Oct 18: 1590.1 (rank #31)Oct 19: 1590.8 (rank #32)Oct 22: 1591.1 (rank #32)Oct 23: 1590.3 (rank #33)Oct 27: 1589.3 (rank #34)Oct 28: 1589.7 (rank #35)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 Diamond95%
PhD-level science multiple choice questions
Better than 99% of 333 tested models. Run Aug 14, 2026.
SimpleQA Verified69%
Short factual questions; rewards not making things up
Better than 91% of 100 tested models. Run Aug 27, 2026.
OTIS Mock AIME 2024-2597%
Competition maths problems in the style of AIME
Better than 87% of 313 tested models. Run Aug 14, 2026.
FrontierMath Tiers 1-372%
Very hard, unpublished research-style maths problems
Better than 79% of 122 tested models. Run Aug 14, 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
#15 of 41914891485–149432,289Oct 28, 2026
WebDev arena
Building web apps, blind human votes
#35 of 15215901583–159614,473Oct 28, 2026
Vision arena
Questions about images, blind human votes
#8 of 16713141305–13235,369Oct 19, 2026
Agent arena
Real multi-step agent sessions
#33 of 57-1.6%-2.5–-0.8%63,681Nov 2, 2026

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-3.7-flash), Nov 4, 2026. Providers can charge differently.