The LLM benchmark aggregator.

Gemini 3.5 Flash Lite

Google

Strongest in Instruction following (#32 of 57), weakest in Core abilities (#202 of 204). Above par in 8 of 22 scopes. Among the models it meets almost everywhere, it finishes behind Claude Fable 5 and Claude Fable 5.1 and ahead of Claude Sonnet 4 and DeepSeek V3.

§ 1 · Profile

What it is good at

Bars run from 50 — the average of the models each source lists — so right of the line is above par. The middle column is the gap to whoever leads that scope.

Human preference62.4−5.1#56/3421/1

Knowledge54.8−8.7#57/1381/2

Academic knowledge55.8−8.1#53/1231/1

Professional49.6−12#84/1681/1

Finance54.1−8.8#59/1511/1

Medical47.5−19.3#94/1401/1

Legal45.4−21.7#100/1511/1

Agents50.2−17.9#115/2682/5

Knowledge work50.2−23.4#81/1782/2

Coding44.9−24.2#117/1652/5

Code generation47.3−22.7#53/771/2

Agentic coding44.2−24.5#111/1572/4

Reasoning38.6−28.3#159/1783/4

Science55.4−8.1#56/1221/1

Reasoning33.8−35.3#136/1402/3

Mathematics32.9−32.8#139/1401/2

Core abilities37.7−29.7#202/2042/3

Instruction following48.8−24.9#32/571/1

Language35.9−35.6#52/571/1

Data analysis26−40.1#57/571/1

General intelligence38.9−31.2#180/2042/3

§ 2 · Head to head

What it beats, and what beats it

The same models turn up scope after scope. Counted once: where both were placed, who finished higher. Bars run right for Gemini 3.5 Flash Lite, left for the other.

GPT-4o Miniwon 16 · lost 2

Mistral Medium 3.5won 14 · lost 3

Claude 3.5 Haikuwon 11 · lost 3

GPT-4.1 Nanowon 14 · lost 4

Llama 4 Scout Instructwon 12 · lost 4

Command Awon 11 · lost 5

GPT OSS 20Bwon 10 · lost 5

GPT-4owon 10 · lost 5

Llama 4 Maverick Instructwon 12 · lost 6

GPT OSS 120Bwon 12 · lost 6

Claude Haiku 4.5won 12 · lost 6

Gemini 3.1 Flash Litewon 11 · lost 6

Gemini 2.5 Flash Litewon 9 · lost 5

GPT-5.4 Nanowon 14 · lost 8

Qwen3.6 27Bwon 10 · lost 6

Nemotron 3 Ultrawon 10 · lost 6

GPT-5.4 Miniwon 13 · lost 8

GPT-5 Nanowon 9 · lost 6

MiniMax M2.7won 9 · lost 6

Grok 4.1 Fastwon 9 · lost 6

Mimo V2.5won 9 · lost 6

Gemma 4 31Bwon 9 · lost 6

O3 Miniwon 10 · lost 7

Mistral Large 3won 10 · lost 8

Grok 4.3won 12 · lost 10

DeepSeek V3won 10 · lost 9

Claude Sonnet 4won 10 · lost 9

GLM-4.7won 8 · lost 8

DeepSeek R1won 9 · lost 9

GLM-4.6won 8 · lost 9

Qwen3 Maxwon 7 · lost 8

GPT-4.1 Miniwon 8 · lost 10

GPT-5 Miniwon 8 · lost 10

DeepSeek V3.2won 8 · lost 10

Gemini 2.0 Flashwon 7 · lost 9

Grok 4 Fastwon 7 · lost 9

Grok 4.20won 6 · lost 8

Claude 3.5 Sonnetwon 6 · lost 8

O1won 6 · lost 8

Grok 3won 6 · lost 8

Kimi K2won 7 · lost 10

Mimo V2.5 Prowon 7 · lost 10

Qwen3.6 Pluswon 9 · lost 13

Claude 3.7 Sonnetwon 6 · lost 9

O4 Miniwon 7 · lost 11

Kimi K2.5won 7 · lost 11

Grok 3 Miniwon 6 · lost 10

MiniMax M2.5won 6 · lost 10

Gemini 2.5 Prowon 7 · lost 12

MiniMax M3won 8 · lost 14

MiniMax M2.1won 5 · lost 9

Qwen3 235B A22B Instructwon 6 · lost 11

Gemini 2.5 Flashwon 6 · lost 12

Qwen3.8 27Bwon 7 · lost 15

Inkling Smallwon 5 · lost 11

Grok 4won 5 · lost 12

GPT-4.1won 5 · lost 12

Kimi K2 Thinkingwon 4 · lost 10

Claude Opus 4won 4 · lost 13

DeepSeek V4 Flashwon 5 · lost 17

O3won 4 · lost 14

GPT-6 Lunawon 4 · lost 15

GLM-5.1won 3 · lost 13

Inklingwon 4 · lost 18

Grok 4.7won 3 · lost 16

Gemini 3 Flashwon 2 · lost 12

GPT-5.2won 3 · lost 18

GPT-5.6 Lunawon 3 · lost 19

GLM-5won 2 · lost 14

GPT-5won 2 · lost 16

Claude Opus 4.5won 2 · lost 19

DeepSeek V4.1 Flashwon 2 · lost 19

Grok 4.6won 2 · lost 20

Qwen3.7 Maxwon 2 · lost 20

Gemini 3.1 Prowon 2 · lost 20

Claude Sonnet 4.5won 1 · lost 17

GPT-6 Solwon 1 · lost 18

Claude Opus 5.5won 1 · lost 18

Claude Opus 4.6won 1 · lost 19

Kimi K2.6won 1 · lost 21

Claude Sonnet 5won 1 · lost 21

Grok 4.5won 1 · lost 21

GPT-5.6 Terrawon 1 · lost 21

Claude Sonnet 4.6won 1 · lost 21

GLM-5.3 Flashwon 1 · lost 21

GLM-5.2won 1 · lost 21

Qwen3.8 Maxwon 1 · lost 21

Claude Opus 5won 1 · lost 21

Gemini 3.8 Flashwon 1 · lost 21

Claude Opus 4.7won 1 · lost 21

Muse Sparkwon 0 · lost 15

GPT-5.1won 0 · lost 16

Gemini 3 Prowon 0 · lost 17

Muse Spark 1.3won 0 · lost 18

GPT-6 Astrawon 0 · lost 19

Muse Spark 1.2won 0 · lost 21

DeepSeek V4 Prowon 0 · lost 22

GPT-5.4won 0 · lost 22

Gemini 3.5 Flashwon 0 · lost 22

GLM-5.3won 0 · lost 22

Claude Opus 4.8won 0 · lost 22

GPT-5.5won 0 · lost 22

Gemini 3.6 Flashwon 0 · lost 22

GPT-5.6 Solwon 0 · lost 22

Gemini 3.7 Flashwon 0 · lost 22

Kimi K3won 0 · lost 22

Muse Spark 1.1won 0 · lost 22

Claude Fable 5.1won 0 · lost 22

Claude Fable 5won 0 · lost 22

§ 3 · Sources

Where the numbers come from

7 publications, 27 figures. Every one links to the page it was read from.

LMArena Text ↗1 measureread 2026-09-26

LMArena Text 1456

Artificial Analysis ↗1 measureread 2026-09-26

Artificial Analysis Intelligence Index 22

GDPval-AA ↗1 measureread 2026-09-26

GDPval-AA 970

AA-Briefcase ↗1 measureread 2026-09-26

AA-Briefcase 648

ARC-AGI-2 ↗1 measureread 2026-09-26

ARC-AGI-2 10.3%

LiveBench ↗8 measuresread 2026-09-26

LiveBench 63.9LiveBench · Reasoning 60.2LiveBench · Coding 76.1LiveBench · Agentic Coding 45.3LiveBench · Mathematics 73.7LiveBench · Data Analysis 53.2LiveBench · Language 71.8LiveBench · Instruction Following 67.2

Vals.ai ↗14 measuresread 2026-09-26

Vals · Legal Research Bench 13.94%Vals · LegalBench 84.07%Vals · Harvey Legal Agent Benchmark 0%Vals · Finance Agent 47.44%Vals · CorpFin 60.68%Vals · TaxEval 72.61%Vals · MortgageTax 68.68%Vals · MedCode 43.49%Vals · MedScribe 70.89%Vals · SWE-bench Verified 75% (Mini-SWE-agent)Vals · Vibe Code Bench 37.16% (OpenHands)Vals · Code Migration 6.15%Vals · GPQA Diamond 83.84%Vals · MMLU Pro 85.84%

Badge

[![PublicAI Index](https://publicai.io/model-index/badge?model=gemini-3-5-flash-lite)](https://publicai.io/model-index/m/gemini-3-5-flash-lite)