The LLM benchmark aggregator.

GPT-4.1 Nano

OpenAI

Strongest in Safe-prompt compliance (#39 of 82), weakest in Agents (#231 of 268). Above par in 6 of 26 scopes. Among the models it meets almost everywhere, it finishes behind Claude Sonnet 5 and GPT-5 and ahead of Llama 4 Scout Instruct and Mistral Large.

§ 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.

Safety52.9−8.6#106/3372/3

Safe-prompt compliance54.2−6.2#39/821/1

Secure code60.4−6.1#65/2741/1

Harm refusal53.8−7.8#92/3002/2

Jailbreak resistance53.6−11.3#136/2721/1

Toxicity avoidance53.4−5.6#145/2721/1

Fairness45.7−24.3#180/3002/2

Knowledge31.5−32#134/1381/2

Academic knowledge27.8−36.1#118/1231/1

Coding42.4−26.7#140/1651/5

Agentic coding40.8−27.9#139/1571/4

Professional39.3−22.3#157/1681/1

Medical41.8−25#120/1401/1

Finance37.4−25.5#138/1511/1

Legal36.9−30.2#141/1511/1

Reasoning38.3−28.6#160/1782/4

Reasoning42.7−26.4#103/1401/3

Science32.4−31.1#108/1221/1

Mathematics39.4−26.3#114/1401/2

Core abilities43.4−24#166/2041/3

General intelligence40.5−29.6#172/2041/3

Human preference49.5−18#198/3421/1

Agents41.2−26.9#231/2682/5

Tool use46.5−27.5#41/811/1

Knowledge work33.8−39.8#165/1781/2

§ 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 GPT-4.1 Nano, left for the other.

Command R Pluswon 14 · lost 3

Gemini 1.5 Flashwon 13 · lost 4

GPT-4o Miniwon 14 · lost 10

Command Awon 13 · lost 10

Mistral Largewon 10 · lost 8

Llama 4 Scout Instructwon 13 · lost 11

Mistral Smallwon 10 · lost 10

Mistral Medium 3.5won 8 · lost 9

Grok 4.3won 11 · lost 13

Gemini 1.5 Prowon 8 · lost 11

Ling 3.0 Flashwon 7 · lost 11

Grok 4.1 Fastwon 8 · lost 14

DeepSeek V3won 8 · lost 17

GPT OSS 20Bwon 7 · lost 15

Nemotron 3 Ultrawon 5 · lost 11

Grok 3won 6 · lost 14

Gemma 4 31Bwon 6 · lost 15

MiniMax M3won 7 · lost 18

Llama 4 Maverick Instructwon 7 · lost 19

GLM-4.5won 5 · lost 14

Gemini 2.0 Flashwon 6 · lost 17

GLM-4.6won 6 · lost 18

DeepSeek V4 Flashwon 6 · lost 18

GLM-5.3 Flashwon 6 · lost 18

GPT OSS 120Bwon 6 · lost 19

GPT-6 Solwon 5 · lost 16

Gemini 3.5 Flash Litewon 4 · lost 14

O3 Miniwon 5 · lost 18

Mistral Large 3won 4 · lost 15

DeepSeek R1won 5 · lost 19

Kimi K2.6won 5 · lost 19

DeepSeek V4 Prowon 5 · lost 19

Gemini 3.6 Flashwon 5 · lost 19

Kimi K2 Thinkingwon 4 · lost 16

Claude 3.5 Haikuwon 4 · lost 16

Gemini 2.5 Flashwon 5 · lost 20

Grok 4won 5 · lost 20

DeepSeek V3.2won 5 · lost 20

Gemini 2.5 Prowon 5 · lost 20

GLM-5.2won 5 · lost 20

GPT-4owon 4 · lost 17

Grok 4 Fastwon 3 · lost 14

Mimo V2.5 Prowon 4 · lost 19

Gemini 3.1 Flash Litewon 3 · lost 15

GPT-5.4 Miniwon 3 · lost 15

Qwen3.7 Maxwon 4 · lost 20

Kimi K2won 4 · lost 21

Mimo V2.6 Prowon 3 · lost 16

GPT-4.1 Miniwon 4 · lost 22

Claude 3.5 Sonnetwon 3 · lost 17

GPT-6 Lunawon 3 · lost 18

GLM-5.1won 3 · lost 19

Qwen3 235B A22B Instructwon 3 · lost 21

Kimi K2.5won 3 · lost 21

Grok 4.5won 3 · lost 21

Gemini 3.5 Flashwon 3 · lost 21

Qwen3.8 Maxwon 3 · lost 21

Gemini 3.8 Flashwon 3 · lost 21

Claude Haiku 4.5won 3 · lost 23

Qwen3.6 Pluswon 2 · lost 16

GPT-5.4 Nanowon 2 · lost 17

Claude Opus 4.6won 2 · lost 18

Claude Sonnet 4.6won 2 · lost 20

Gemini 3 Prowon 2 · lost 20

Claude Opus 5won 2 · lost 22

Muse Spark 1.1won 2 · lost 22

GPT-4.1won 2 · lost 23

Inkling Smallwon 1 · lost 15

GPT-6 Astrawon 1 · lost 15

GLM-5won 1 · lost 16

Gemini 2.5 Flash Litewon 1 · lost 18

Claude Opus 4.5won 1 · lost 18

Gemini 3.1 Prowon 1 · lost 18

Claude 3.7 Sonnetwon 1 · lost 21

GPT-5 Nanowon 1 · lost 22

Claude Opus 4won 1 · lost 22

GPT-5.1won 1 · lost 22

Grok 4.6won 1 · lost 23

GPT-5.4won 1 · lost 23

Claude Opus 4.8won 1 · lost 23

GPT-5.5won 1 · lost 23

GPT-5.6 Solwon 1 · lost 23

Claude Opus 4.7won 1 · lost 23

O4 Miniwon 1 · lost 24

Claude Sonnet 4won 1 · lost 24

O3won 1 · lost 24

Inklingwon 1 · lost 24

GPT-5.6 Lunawon 1 · lost 24

GPT-5.6 Terrawon 1 · lost 24

GPT-5 Miniwon 1 · lost 25

Claude Sonnet 4.5won 1 · lost 25

MiniMax M2.5won 0 · lost 16

GLM-4.7won 0 · lost 16

DeepSeek V4.1 Flashwon 0 · lost 17

Muse Spark 1.2won 0 · lost 17

GLM-5.3won 0 · lost 18

Gemini 3.7 Flashwon 0 · lost 18

Kimi K3won 0 · lost 18

Claude Fable 5.1won 0 · lost 18

Claude Fable 5won 0 · lost 18

Qwen3.8 27Bwon 0 · lost 19

O1won 0 · lost 21

MiniMax M2.7won 0 · lost 21

Grok 4.7won 0 · lost 21

Claude Opus 5.5won 0 · lost 21

GPT-5.2won 0 · lost 24

GPT-5won 0 · lost 25

Claude Sonnet 5won 0 · lost 25

§ 3 · Sources

Where the numbers come from

9 publications, 25 figures. Every one links to the page it was read from.

LMArena Text ↗1 measureread 2026-09-26

LMArena Text 1322

GDPval-AA ↗1 measureread 2026-09-26

GDPval-AA -228

ARC-AGI-2 ↗1 measureread 2026-09-26

ARC-AGI-2 0%

Aider polyglot ↗1 measureread 2026-09-26

Aider polyglot 8.9%

BFCL ↗1 measureread 2026-09-26

BFCL v4 33.05%

Kagi LLM Benchmark ↗1 measureread 2026-09-26

Kagi LLM Benchmark 33.3%

Vals.ai ↗8 measuresread 2026-09-26

Vals · LegalBench 61.06%Vals · CorpFin 42.08%Vals · TaxEval 60.75%Vals · MortgageTax 52.82%Vals · MedQA 68.22%Vals · GPQA Diamond 50.76%Vals · MMLU Pro 63.48%Vals · AIME 26.46%

HELM Safety ↗5 measuresread 2026-09-26

HELM Safety · HarmBench 86.8%HELM Safety · SimpleSafetyTests 99%HELM Safety · Anthropic Red Team 99.6%HELM Safety · BBQ 87.5%HELM Safety · XSTest 96%

Enkrypt AI Safety Leaderboard ↗6 measuresread 2026-09-26

Enkrypt · Jailbreak risk 9.7%Enkrypt · Harmful content risk 40%Enkrypt · CBRN risk 10.5%Enkrypt · Toxicity risk 3.9%Enkrypt · Bias risk 87.1%Enkrypt · Insecure code risk 12.4%

Badge

[![PublicAI Index](https://publicai.io/model-index/badge?model=gpt-4-1-nano)](https://publicai.io/model-index/m/gpt-4-1-nano)