GoogleUnited States· released Jul 2026

Gemini 3.5 Flash-Lite

Name: Gemini 3.5 Flash-Lite
Author: Google

Provisional: 13 comparable tests so far. Ranked once it reaches 6 across 3 counting categories.

Google, United States. One of 14 models from this lab on the Index.

Third-party publishedLow confidence (thin coverage)

Snapshot September 8, 2026

OpenCharts Index

32.5

Provisional: not enough comparable tests or counting categories to rank yet · 13 comparable tests · 2 counting categories

Drop any single test and the Index lands between 24.9 and 38.6.

Needs more results (3 of 8 so far)

Averaging 12.8 on the 3 it has; the score opens at 4 of 8.

Distance to today's frontier on the hardest tests. Not a measure of intelligence.

What it's known for

Gemini 3.5 Flash-Lite, in 13 results.

Strongest in reasoning (36.9) and math (28.0). It trails the frontier most in math, 72.0% behind on average. No comparable results yet in knowledge, agentic and long context. Below 40% of the best published results, on average.

Strongest category

Reasoning

Hard, novel problems: graduate science, abstract puzzles, expert exams.

36.9

GPQA Diamond83.3% · 82% of best
ARC-AGI-153.5% · 54% of best
ARC-AGI-210.3% · 11% of best
CritPt0.0% · 0% of best

Mean of 4 of the category's 6 comparable tests. Counts toward the Index.

Best single result

Vision Arena

Answer prompts that include an image; real users vote blind between two models' answers.

1,266

43% expected win rate against the board leader (1,313) · #23 of 54.

Seeing is half of most real tasks: screenshots, documents, photos and charts.

Where it trails

FrontierMath Tier 4

Solve the hardest FrontierMath tier: problems that take expert mathematicians days.

0.0%

100.0% behind the best published result (97.6%) · #50 of 51.

The deepest end of the set. Progress here signals genuinely new capability.

Not measured yet

No comparable result yet in these 3 categories. A blank is a blank, never a zero, and it does not lower the Index.

Knowledge
Agentic
Long context

Covered, but not averaged into the Index:

Coding3 of 7 tests · needs 4 · mean 43.9
Multimodalsingle-test category, shown beside the Index · 86.7
Human preferencesingle-test category, shown beside the Index · 85.6

Every score, with its source

See it at work

What Gemini 3.5 Flash-Lite was asked to do, and how it did.

Every test it has taken, by category, with the kind of task it faced, who produced the number and where the result landed against the best published one. The examples are original and illustrative, never items from the datasets themselves.

Multimodal · mean 86.7 across 1 comparable test · a single-test category, shown beside the Index and never averaged into it

Vision ArenaLeaderboard

Answer prompts that include an image; real users vote blind between two models' answers.

1,266

43% expected win rate against the board leader (1,313)
#23 of 54

board 2026-08-27

Source: Arena

Every result is read against the best published one on its test: percent scores as a share of the best above chance, Arena ratings as the expected win rate against the board leader, open-ended values on a log scale. Sitting a harder exam never lowers a model. Every number links to the publisher that produced it.

Head to head

Gemini 3.5 Flash-Lite against whoever you pick.

Choose a rival. Every counted test both have taken appears side by side as a share of the best published result on that test, with the category means above. A win is a higher share; a gap under 2 points is a tie, because one item on a 45-problem exam is 2.2 points and publishers' own standard errors are of that order.

Gemini 3.5 Flash-Lite

provisional·Index 32.5F

0 : 11

wins · 0 ties · 11 shared

GPT-6 Astra

#1·Index 99.0A+

GPT-6 Astra comes out ahead on 11 of the 11 tests both have taken.

Category means

Reasoning
36.9
99.6
Knowledge
—
100.0
Coding
43.9
97.7
Math
28.0
99.8
Agentic
—
98.5
Multimodal
86.7
—
Human preference
85.6
—

Shared tests · biggest gaps first

FrontierMath Tier 4Math
0.0%
97.6%
−100.0
CritPtReasoning
0.0%
31.7%
−98.2
ARC-AGI-2Reasoning
10.3%
95.0%
−89.2
ProofBenchMath
13.0%
99.0%
−86.0
Code Arena (WebDev)Coding
1,449
1,797
−76.2
FrontierMath (Tiers 1–3)Math
26.0%
93.7%
−72.3
WeirdMLCoding
39.0%
92.9%
−58.0
ARC-AGI-1Reasoning
53.5%
98.5%
−45.7
Mock AIME 2024–2025Math
71.1%
100.0%
−28.9
SciCodeCoding
40.9%
56.5%
−25.1
GPQA DiamondReasoning
83.3%
95.8%
−17.6

Bars are distances to the best published result on each test (percent scores above chance, Arena ratings as win rate against the leader, open-ended values on a log scale). Raw values as the publishers report them.

Open GPT-6 Astra

Scores

Every test, every source

The best published run per benchmark, the raw value as the publisher reports it, who produced the number, how close it comes to the best published result on that test, and where the model sits among every model scored on it. Percent scores are read above chance, Arena ratings as a win rate against the board leader, open-ended values on a log scale. A test with too few models to compare against is shown but not counted.

Category means

Reasoning36.9 · 4/6
Knowledge—
Coding43.9 · 3/7
Math28.0 · 4/5
Agentic—
Multimodalbeside86.7 · 1/1
Human preferencebeside85.6 · 1/1
Long context—

Mean · tests taken of the category's comparable tests. A faded category either rests on fewer than half of them or is a single-test category (marked “beside”), which is shown next to the Index and never averaged into it.

GPQA DiamondEpoch-runReasoning

83.3%

82.4% of the best (95.8%), above chance
21th percentile of 78 · n = 198

high

Source: Epoch AI — AI Benchmarking Hub

ARC-AGI-2LeaderboardReasoning

10.3%

10.8% of the best (95.0%)
20th percentile of 51 · n = 120

high

Source: Epoch AI — AI Benchmarking Hub

ARC-AGI-1LeaderboardReasoning

53.5%