VerdictPal
Join

Models / Google

Gemini 3.1 Flash Lite

Gemini 3.1 · Released 2026-05-07

Google's cheapest 1M-context Gemini. $0.25/$1.50 per 1M tokens. Vals Index 35.24 (#16). Volume tier for classification and routing.

High-volume preprocessing, tagging, and cheap RAG front doors before escalating to Pro.

#21 of 21 on Vals Index · current snapshot
35 Vals Index · 11 benchmark rows · 2 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite43
Context1M
Input / 1M$0.25
Output / 1M$1.5
Knowledge cutoff2025-01-31
Output speed315 t/s
TTFT (default API)4.90s
Statussolid
Gemini
ReasoningCodingAgenticLong context
Reasoning
82
Coding
42
Agentic
35
Long context
65

56average across 4 tested families

Benchmark placements

Where Gemini 3.1 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#4/ 69Artificial Analysis2026-07-21
IFBenchReasoning#8/ 5777Artificial Analysis2026-07-21
Vals IndexAgentic#20/ 2035Vals AI — Vals Index2026-06-04
AA time to first tokenPerformance#25/ 69Artificial Analysis2026-07-21
AA-LCRLong context#38/ 6465Artificial Analysis2026-07-21
GPQA DiamondReasoning#44/ 6982Artificial Analysis2026-07-21
SciCodeCoding#48/ 6542Artificial Analysis2026-07-21
Humanity's Last ExamReasoning#49/ 6516Artificial Analysis2026-07-21
Artificial Analysis Intelligence IndexReasoning#52/ 6725Artificial Analysis2026-07-21
τ³-Bench BankingAgentic#58/ 649Artificial Analysis2026-07-21
Terminal-BenchAgentic#59/ 6931Artificial Analysis2026-07-21
Family context

The three highest-scoring carded models in each capability family. Where Gemini 3.1 Flash Lite shows up, it's highlighted.

ReasoningGemini 3.1 Flash Lite · 82
  1. 1
    Claude Mythos Preview
    95
  2. 2
    GPT-5.6 Sol
    94
  3. 3
    Kimi K3
    94
CodingGemini 3.1 Flash Lite · 42
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticGemini 3.1 Flash Lite · 35
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextGemini 3.1 Flash Lite · 65
  1. 1
    Kimi K3
    75
  2. 2
    GPT-5.1
    75
  3. 3
    GPT-5.6 Sol
    74
Newest receipts

Benchmark rows added to the public ledger for Gemini 3.1 Flash Lite in the last 120 days. Older rows live in the full table below.

11 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context65.33%Artificial Analysis2
AA output speedPerformance315 t/sArtificial Analysis2
AA time to first tokenPerformance4.90sArtificial Analysis2
Artificial Analysis Intelligence IndexReasoning25%Artificial Analysis2
GPQA DiamondReasoning82.2%Artificial Analysis2
Humanity's Last ExamReasoning16.2%Artificial Analysis2
IFBenchReasoning77.21%Artificial Analysis2
SciCodeCoding41.9%Artificial Analysis2
τ³-Bench BankingAgentic8.66%Artificial Analysis2
Terminal-BenchAgentic31.09%Artificial Analysis2
Vals IndexAgentic35.24%Vals AI — Vals Index49
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.

Reasoning82
Coding42
Agentic35
Long context65
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover or tab any dot for name, score, and input price.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMiniMaxxAIMetaZhipuXiaomiMeituanCohere

Full benchmark ledger

Every catalog benchmark for Gemini 3.1 Flash Lite. Scores link to the original source; gaps mean no public row exists yet.

11 sourced rows

11 of 32 catalog benchmarks have a sourced row for Gemini 3.1 Flash Lite.

Reasoning

Coding

Agentic

Long context

Performance

Sources