VerdictPal
Join

Models / Google

Gemini 3.5 Flash-Lite

Gemini 3.5 · Released 2026-07-21

AA Intelligence Index 36.5. Listed on Artificial Analysis with API pricing $0.3/$2.5 per 1M tokens. Benchmark rows sync from the AA snapshot — see the ledger on this page.

Frontier model tracked on Artificial Analysis. Use the benchmark ledger below for sourced scores; we do not infer numbers beyond published rows.

#109 of 184 on AA Index · current snapshot
23 AA Index · 9 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite44
Context128K
Input / 1M$0.30
Output / 1M$2.5
Knowledge cutoffopen
Output speed365 t/s
TTFT (default API)7.81s
Statussolid

Family profile

Best published score in each covered benchmark family.

64/100 avg
Reasoning
84
Coding
41
Agentic
54
Long context
76

4 tested benchmark families

Benchmark placements

Where Gemini 3.5 Flash-Lite places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.

BenchmarkFamilyRankScoreSourceDate
AA output speedPerformance#1/ 190Artificial Analysis2026-09-10
AA time to first tokenPerformance#22/ 190Artificial Analysis2026-09-10
τ³-Bench BankingAgentic#68/ 11118Artificial Analysis2026-09-10
SciCodeCoding#74/ 9441Artificial Analysis2026-09-10
AA-LCRLong context#75/ 18276Artificial Analysis2026-09-10
Terminal-BenchAgentic#87/ 18954Artificial Analysis2026-09-10
Artificial Analysis Intelligence IndexReasoning#113/ 18823Artificial Analysis2026-09-10
GPQA DiamondReasoning#116/ 19084Artificial Analysis2026-09-10
Humanity's Last ExamReasoning#131/ 18519Artificial Analysis2026-09-10
Family context

The three highest-scoring models with pages in each capability family. Where Gemini 3.5 Flash-Lite shows up, it's highlighted.

ReasoningGemini 3.5 Flash-Lite · 84
  1. 1
    GPT-6 Astra
    96
  2. 2
    Claude Mythos Preview
    95
  3. 3
    Gemini 3.7 Flash
    95
CodingGemini 3.5 Flash-Lite · 41
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticGemini 3.5 Flash-Lite · 54
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextGemini 3.5 Flash-Lite · 76
  1. 1
    Kimi K3
    89
  2. 2
    Claude Fable 5.1
    85
  3. 3
    GPT-5.5 (high)
    84
Newest receipts

Benchmark rows added to the public ledger for Gemini 3.5 Flash-Lite in the last 120 days. Older rows live in the full table below.

9 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context76%Artificial Analysis4
AA output speedPerformance365 t/sArtificial Analysis4
AA time to first tokenPerformance7.81sArtificial Analysis4
Artificial Analysis Intelligence IndexReasoning22.7%Artificial Analysis4
GPQA DiamondReasoning83.8%Artificial Analysis4
Humanity's Last ExamReasoning18.8%Artificial Analysis4
SciCodeCoding41.3%Artificial Analysis4
τ³-Bench BankingAgentic17.53%Artificial Analysis4
Terminal-BenchAgentic53.56%Artificial Analysis4
Family coverage

A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.

Reasoning84
Coding41
Agentic54
Long context76
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaxAIMiniMaxZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for Gemini 3.5 Flash-Lite. Scores link to the original source; gaps mean no public row exists yet.

9 sourced rows

9 of 37 catalog benchmarks have a sourced row for Gemini 3.5 Flash-Lite.

Reasoning

Coding

Agentic

Long context

Performance

Sources