Request a pilot
‹ PublicAI Index

The LLM benchmark aggregator.

Gemini 3.7 Flash

Google

Strongest in Instruction following (#2 of 57), weakest in General intelligence (#53 of 204). Above par in 21 of 23 scopes. Among the models it meets almost everywhere, it finishes behind Claude Fable 5.1 and Claude Fable 5 and ahead of Muse Spark 1.1 and GLM-5.3.

§ 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.

Knowledge59.3#7/138
Academic knowledge61.1#6/123
Human preference65.5#13/342
Human preference65.5#13/342
Reasoning58.2#20/178
Science62.5#5/122
Reasoning59.8#22/140
Mathematics54.9#52/140
Core abilities57.5#23/204
Instruction following71.1#2/57
Language61.7#11/57
Data analysis40.9#47/57
General intelligence56.4#53/204
Professional56.4#23/168
IT operations42.7#6/11
Medical59.7#11/140
Finance58.4#14/151
Legal57.2#25/151
Coding53.8#39/165
Code generation53.1#36/77
Agentic coding54#47/157
Agents57.7#47/268
Knowledge work60#36/178

§ 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 3.7 Flash, left for the other.

Claude 3.5 Haikuwon 14 · lost 0
Claude 3.5 Sonnetwon 14 · lost 0
Gemini 2.5 Flash Litewon 14 · lost 0
MiniMax M2.1won 14 · lost 0
Grok 3won 14 · lost 0
GPT-4owon 15 · lost 0
GPT-5 Nanowon 15 · lost 0
Mimo V2.5won 15 · lost 0
Nemotron 3 Ultrawon 16 · lost 0
Llama 4 Scout Instructwon 16 · lost 0
Command Awon 16 · lost 0
Gemini 2.0 Flashwon 16 · lost 0
Inkling Smallwon 16 · lost 0
Mistral Medium 3.5won 17 · lost 0
Mimo V2.5 Prowon 17 · lost 0
GPT-4o Miniwon 18 · lost 0
GPT-4.1 Nanowon 18 · lost 0
GPT-4.1 Miniwon 18 · lost 0
Mistral Large 3won 18 · lost 0
Claude Haiku 4.5won 18 · lost 0
DeepSeek V3.2won 18 · lost 0
DeepSeek V3won 19 · lost 0
Grok 4.3won 22 · lost 0
Gemini 3.5 Flash Litewon 22 · lost 0
Kimi K2.6won 22 · lost 0
Gemini 3.6 Flashwon 22 · lost 0
GPT-5.4 Nanowon 21 · lost 1
Inklingwon 21 · lost 1
Qwen3.6 Pluswon 21 · lost 1
Qwen3.7 Maxwon 21 · lost 1
Gemini 3.5 Flashwon 21 · lost 1
GPT-5.4 Miniwon 20 · lost 1
GPT OSS 120Bwon 17 · lost 1
Gemini 2.5 Flashwon 17 · lost 1
Kimi K2won 16 · lost 1
Gemini 3.1 Flash Litewon 16 · lost 1
Qwen3.6 27Bwon 15 · lost 1
MiniMax M2.5won 15 · lost 1
GLM-4.7won 15 · lost 1
GLM-5.1won 15 · lost 1
GPT OSS 20Bwon 14 · lost 1
MiniMax M2.7won 14 · lost 1
Qwen3 Maxwon 14 · lost 1
Gemma 4 31Bwon 14 · lost 1
Kimi K2 Thinkingwon 13 · lost 1
O1won 13 · lost 1
Gemini 3 Flashwon 13 · lost 1
MiniMax M3won 20 · lost 2
Claude Sonnet 4won 17 · lost 2
Claude Sonnet 4.5won 16 · lost 2
GPT-4.1won 15 · lost 2
Qwen3 235B A22B Instructwon 15 · lost 2
GLM-4.6won 15 · lost 2
Grok 3 Miniwon 14 · lost 2
Grok 4 Fastwon 14 · lost 2
Claude 3.7 Sonnetwon 13 · lost 2
Grok 4.1 Fastwon 13 · lost 2
Claude Sonnet 4.6won 19 · lost 3
Gemini 2.5 Prowon 16 · lost 3
GPT-5 Miniwon 15 · lost 3
Kimi K2.5won 15 · lost 3
Claude Opus 4won 14 · lost 3
Qwen3.8 27Bwon 18 · lost 4
DeepSeek V4 Flashwon 18 · lost 4
GLM-5won 13 · lost 3
Grok 4.20won 11 · lost 3
Grok 4.5won 18 · lost 5
O4 Miniwon 14 · lost 4
DeepSeek R1won 14 · lost 4
GPT-5won 14 · lost 4
GLM-5.3 Flashwon 17 · lost 5
GPT-5.4won 17 · lost 5
O3 Miniwon 13 · lost 4
Grok 4won 13 · lost 4
GPT-5.2won 16 · lost 5
GPT-5.1won 12 · lost 4
GLM-5.2won 17 · lost 6
Muse Sparkwon 11 · lost 4
GPT-5.6 Lunawon 16 · lost 6
DeepSeek V4 Prowon 16 · lost 6
O3won 13 · lost 5
Claude Opus 4.5won 15 · lost 6
GPT-6 Lunawon 13 · lost 6
Qwen3.8 Maxwon 15 · lost 7
Gemini 3.1 Prowon 15 · lost 7
Gemini 3 Prowon 11 · lost 6
Claude Sonnet 5won 14 · lost 8
GPT-5.6 Terrawon 14 · lost 8
DeepSeek V4.1 Flashwon 14 · lost 8
Claude Opus 4.6won 12 · lost 8
GLM-5.3won 13 · lost 9
Muse Spark 1.1won 13 · lost 9
Grok 4.7won 9 · lost 10
Grok 4.6won 10 · lost 12
GPT-5.5won 10 · lost 13
Muse Spark 1.2won 9 · lost 12
GPT-6 Solwon 8 · lost 11
Claude Opus 4.8won 9 · lost 13
Claude Opus 4.7won 9 · lost 13
GPT-5.6 Solwon 9 · lost 14
Kimi K3won 8 · lost 14
GPT-6 Astrawon 7 · lost 13
Gemini 3.8 Flashwon 7 · lost 15
Claude Opus 5.5won 3 · lost 17
Claude Opus 5won 3 · lost 20
Muse Spark 1.3won 2 · lost 16
Claude Fable 5won 2 · lost 20
Claude Fable 5.1won 2 · lost 21

§ 3 · Sources

Where the numbers come from

7 publications, 28 figures. Every one links to the page it was read from.

LMArena Text ↗1 measureread 2026-09-26
LMArena Text 1488
GDPval-AA ↗1 measureread 2026-09-26
GDPval-AA 1371
AA-Briefcase ↗1 measureread 2026-09-26
AA-Briefcase 1107
Terminal-Bench ↗1 measureread 2026-09-26
Terminal-Bench 11.2% (mini-SWE-agent)
ARC-AGI-2 ↗1 measureread 2026-09-26
ARC-AGI-2 84.6%
LiveBench ↗8 measuresread 2026-09-26
LiveBench 78.8LiveBench · Reasoning 87.8LiveBench · Coding 78.9LiveBench · Agentic Coding 58.3LiveBench · Mathematics 93.5LiveBench · Data Analysis 68LiveBench · Language 85.5LiveBench · Instruction Following 79.9
Vals.ai ↗15 measuresread 2026-09-26
Vals · Legal Research Bench 34.62%Vals · LegalBench 87.26%Vals · Harvey Legal Agent Benchmark 8.75%Vals · Finance Agent 59.04%Vals · TaxEval 74.73%Vals · MortgageTax 66.65%Vals · MedCode 53.39%Vals · MedScribe 83.94%Vals · SRE Bench 4.58%Vals · SWE-bench Verified 80.8% (Mini-SWE-agent)Vals · Vibe Code Bench 70.39% (OpenHands)Vals · Code Migration 34.8%Vals · GPQA Diamond 93.94%Vals · MMLU Pro 90.12%Vals · ProofBench 58%

Badge

PublicAI Index badge for Gemini 3.7 Flash[![PublicAI Index](https://publicai.io/model-index/badge?model=gemini-3-7-flash)](https://publicai.io/model-index/m/gemini-3-7-flash)