Automated page. Written and translated automatically by AI and checked against the sources by software; no human editor. SI-IQ is an index built from public benchmark results, not an IQ test. How it works

How smart is Gemini 3.5 Flash-Lite?

109 SI-IQ · 90% interval 106–113
Rank 61 of 80 ranked models · Plausible rank range 45–67

Gemini 3.5 Flash-Lite is a model from Google DeepMind, released on Jul 21, 2026. Its SI-IQ is 109 (90% interval 106–113), estimated from 7 benchmark results by 2 independent evaluators. Its strongest area is Reasoning and its weakest is Math.

Facts

Developer: Google DeepMind
Released: Jul 21, 2026
Access: API access
Benchmarks used: 7 results from 2 evaluators
API price: $0.30 input / $2.50 output per 1M tokens (developer's price list, Oct 18, 2026)
Context window: 1,048,576 tokens

Ability by area (SI-IQ, 90% interval)

Every benchmark result we used

Each score is one value exactly as the source published it: for Epoch AI the best of its run settings, for OpenRouter the median hosting provider (the developer's own hosting when it ran the test). “Implied SI-IQ” is the ability that this single result points to; the overall SI-IQ is their precision-weighted average.

Benchmark	Area	Score	Implied SI-IQ	Evaluated by	As listed by the source	Retrieved	Source
Chess Puzzles	Reasoning	21.0%	113	Epoch AI	`gemini-3.5-flash-lite_low`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
Mystery Game Puzzles	Reasoning	19.0%	112	Epoch AI	`gemini-3.5-flash-lite_low`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
FrontierMath Tier 4	Math	0.0%	102	Epoch AI	`gemini-3.5-flash-lite_high`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
FrontierMath Tiers 1–3	Math	26.0%	109	Epoch AI	`gemini-3.5-flash-lite_high`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
OTIS Mock AIME 2024–2025	Math	71.1%	103	Epoch AI	`gemini-3.5-flash-lite_high`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
GPQA Diamond	Knowledge	83.3%	112	Epoch AI	`gemini-3.5-flash-lite_high`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
GPQA Diamond (OpenRouter run)	Knowledge	84.0%	117	OpenRouter	`google/gemini-3.5-flash-lite-20260721` Google · first-party provider (2 of 2 rows), lower median	Oct 18, 2026	OpenRouter benchmark datasets · data file
τ²-bench Airline (OpenRouter run)	Agents	73.5%	126	OpenRouter	`google/gemini-3.5-flash-lite-20260721` Google AI Studio · first-party provider (2 of 2 rows), lower median	Oct 18, 2026	OpenRouter benchmark datasets · data file

Human preference (Arena)

On the Arena leaderboard, where people vote between two anonymous answers, Gemini 3.5 Flash-Lite has a rating of 1,455 (1,450–1,459) from 35,851 votes (published Oct 15, 2026). Human preference is a different measure from benchmark ability and is not part of SI-IQ. Arena (Hugging Face)

Models with similar SI-IQ

Model	SI-IQ
Claude Sonnet 4.5Anthropic	110	Gemini 3.5 Flash-Lite vs Claude Sonnet 4.5
Gemini 2.5 Pro (Jun 2025)Google DeepMind	108	Gemini 3.5 Flash-Lite vs Gemini 2.5 Pro (Jun 2025)
MiniMax-M3MiniMax	108	Gemini 3.5 Flash-Lite vs MiniMax-M3
Qwen 3.6 35B-A3BAlibaba	111	Gemini 3.5 Flash-Lite vs Qwen 3.6 35B-A3B
Qwen3-235B-A22B-Thinking (Jul 2025)Alibaba	111	Gemini 3.5 Flash-Lite vs Qwen3-235B-A22B-Thinking (Jul 2025)

Computed with SI-IQ method version 1.0.0. Read the full methodology

Data sources: Arena leaderboard dataset on Hugging Face (CC BY 4.0); Epoch AI, ‘Capabilities & benchmarking’ (CC BY 4.0); API list prices via LiteLLM's price table (MIT); each price links to the developer's pricing page; Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter..