The LLM benchmark aggregator.

Llama 4 Maverick Instruct

Meta · 402B · open weights

Strongest in Safe-prompt compliance (#33 of 82), weakest in Agents (#246 of 298). Above par in 8 of 27 scopes. Among the models it meets almost everywhere, it finishes behind Claude Opus 4.8 and Grok 4.7 and ahead of Gemini 2.0 Flash and GPT OSS 20B.

§ 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.

Core abilities51.1−14.2#86/1991/4

General intelligence51.6−17.8#74/1781/3

Safety52.4−9#119/3293/3

Safe-prompt compliance55.3−5.1#33/821/1

Factual grounding54.4−16.3#40/1041/1

Jailbreak resistance59.9−5.1#48/2681/1

Toxicity avoidance55.8−3.2#84/2681/1

Harm refusal53.2−8.3#102/2922/2

Fairness47.6−22.4#146/2922/2

Secure code41.6−24.6#207/2701/1

Knowledge49.1−13.4#126/1971/3

Academic knowledge47.7−16.2#89/1231/1

Coding44−22.2#135/1791/6

Agentic coding43.4−23.5#134/1731/5

Reasoning40−25.4#168/1953/5

Science45.4−18.1#90/1221/1

Mathematics39.1−24.7#123/1521/2

Reasoning37.8−31.2#128/1472/3

Professional41.5−20.9#177/1941/2

Legal49.6−16.3#92/1731/1

Finance44.7−17.7#125/1621/1

Medical31.3−35.2#146/1491/1

Human preference49.7−19.1#201/3541/1

Agents43.1−23.3#246/2982/6

Tool use49.6−24.4#36/811/1

Knowledge work31.8−38.9#199/2081/2

§ 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 Llama 4 Maverick Instruct, left for the other.

Gemini 1.5 Flashwon 15 · lost 2

Llama 3.3 70B Instructwon 18 · lost 3

Llama 4 Scout Instructwon 21 · lost 4

Command R+won 15 · lost 3

GPT-4o miniwon 18 · lost 6

GPT-4.1 nanowon 19 · lost 7

Mistral Medium 3.5won 12 · lost 5

Command Awon 16 · lost 8

Magistral Small 1.2won 11 · lost 6

Gemini 1.5 Prowon 12 · lost 7

Gemma 4 31Bwon 13 · lost 8

GPT OSS 20Bwon 13 · lost 9

Gemini 2.0 Flashwon 13 · lost 10

Claude 3.5 Haikuwon 10 · lost 10

GPT OSS 120Bwon 12 · lost 14

Mistral Large 3won 9 · lost 11

NVIDIA Nemotron 3 Ultra 550B A55Bwon 10 · lost 14

GLM-4.6won 10 · lost 15

GPT-4owon 9 · lost 15

Grok 4.3won 8 · lost 14

Kimi K2.5won 9 · lost 16

Ling 3.0 Flashwon 6 · lost 11

MiMo V2.6 Flashwon 7 · lost 13

O3 Miniwon 8 · lost 15

Grok 4.1 Fastwon 8 · lost 15

DeepSeek V3won 9 · lost 17

Gemini 3.1 Flash-Litewon 6 · lost 12

DeepSeek V4 Flashwon 8 · lost 16

DeepSeek V4 Prowon 8 · lost 17

Kimi K2won 8 · lost 18

Kimi K2.6won 7 · lost 16

Gemini 2.5 Flash-Litewon 6 · lost 14

GPT-5.4 nanowon 6 · lost 14

MiniMax M3won 7 · lost 17

GLM-5.3 Flashwon 7 · lost 17

Mistral Large 4won 6 · lost 15

MiMo V2.6 Prowon 6 · lost 15

Claude Haiku 4.5won 7 · lost 18

DeepSeek R1won 7 · lost 18

MiniMax M2.5won 5 · lost 13

GPT-6 Lunawon 6 · lost 16

GPT-4.1 miniwon 7 · lost 19

DeepSeek V3.2won 7 · lost 19

GLM-4.5won 5 · lost 14

Claude 3.5 Sonnetwon 5 · lost 15

GPT-5 nanowon 6 · lost 18

Grok 3won 6 · lost 18

Inklingwon 6 · lost 18

GLM-5.2won 6 · lost 18

GPT-4.1won 6 · lost 20

MiniMax M2.7won 5 · lost 17

Grok 4 Fastwon 4 · lost 14

Inkling Smallwon 4 · lost 14

Gemini 3.5 Flash-Litewon 4 · lost 14

Gemini 3.6 Flashwon 5 · lost 18

Gemini 3.8 Flashwon 5 · lost 19

Kimi K2 Thinkingwon 4 · lost 16

Qwen3 235B A22B Instructwon 5 · lost 21

Gemini 2.5 Prowon 5 · lost 21

MiMo V2.5 Prowon 4 · lost 17

GPT-5 miniwon 5 · lost 22

GPT-6 Solwon 4 · lost 18

GLM-5.1won 4 · lost 18

Qwen3.7 Maxwon 4 · lost 19

Gemini 3.5 Flashwon 4 · lost 19

GLM-4.7won 3 · lost 15

GLM-5won 3 · lost 15

GPT-6 Astrawon 3 · lost 15

GPT-5.6 Lunawon 4 · lost 20

Qwen3.8 Maxwon 4 · lost 20

Grok 4won 4 · lost 21

GPT-5.4 miniwon 3 · lost 16

Gemini 2.5 Flashwon 4 · lost 22

Claude Opus 4.5won 3 · lost 17

Claude Sonnet 4.6won 3 · lost 19

Gemini 3 Prowon 3 · lost 20

GPT-5.1won 3 · lost 21

Grok 4.6won 3 · lost 21

Grok 4.5won 3 · lost 21

GPT-5.6 Terrawon 3 · lost 21

GPT-5.4won 3 · lost 22

GPT-5.5won 3 · lost 22

GPT-5.6 Solwon 3 · lost 22

Gemini 4 Argonwon 2 · lost 15

O4 Miniwon 3 · lost 23

Qwen3.8 27Bwon 2 · lost 16

Gemini 3.1 Prowon 2 · lost 17

Claude Opus 4.6won 2 · lost 19

Claude 3.7 Sonnetwon 2 · lost 20

Claude Opus 5won 2 · lost 20

Muse Spark 1.1won 2 · lost 20

Claude Opus 5.5won 2 · lost 20

GPT-5.2won 2 · lost 23

GPT-5won 2 · lost 24

Claude Sonnet 4.5won 2 · lost 25

Kimi K3won 1 · lost 17

Grok 3 Miniwon 1 · lost 19

O1won 1 · lost 20

Claude Sonnet 5won 1 · lost 22

Claude Opus 4won 1 · lost 23

O3won 1 · lost 24

Claude Opus 4.7won 1 · lost 24

Claude Sonnet 4won 1 · lost 25

Gemini 3.7 Flashwon 0 · lost 17

DeepSeek V4.1 Flashwon 0 · lost 18

GLM-5.3won 0 · lost 18

Claude Fable 5.1won 0 · lost 18

Claude Fable 5won 0 · lost 18

Grok 4.7won 0 · lost 21

Claude Opus 4.8won 0 · lost 24

§ 3 · Sources

Where the numbers come from

11 publications, 29 figures. Every one links to the page it was read from.

LMArena Text ↗1 measureread 2026-11-10

LMArena Text 1327

GDPval-AA ↗1 measureread 2026-11-10

GDPval-AA -268

ARC-AGI-2 ↗1 measureread 2026-11-10

ARC-AGI-2 0%

Aider polyglot ↗1 measureread 2026-11-10

Aider polyglot 15.6%

BFCL ↗1 measureread 2026-11-10

BFCL v4 37.29%

Kagi LLM Benchmark ↗1 measureread 2026-11-10

Kagi LLM Benchmark 55.9%

SimpleBench ↗1 measureread 2026-11-10

SimpleBench 27.7%

Vals.ai ↗10 measuresread 2026-11-10

Vals · LegalBench 77.81%Vals · CorpFin 49.73%Vals · TaxEval 66.56%Vals · MortgageTax 58.51%Vals · MedQA 43.3%Vals · MedCode 36.51%Vals · MedScribe 54.22%Vals · GPQA Diamond 69.44%Vals · MMLU Pro 79.42%Vals · AIME 25.21%

HELM Safety ↗5 measuresread 2026-11-10

HELM Safety · HarmBench 66.1%HELM Safety · SimpleSafetyTests 99.3%HELM Safety · Anthropic Red Team 98.2%HELM Safety · BBQ 93%HELM Safety · XSTest 96.5%

Enkrypt AI Safety Leaderboard ↗6 measuresread 2026-11-10

Enkrypt · Jailbreak risk 4.5%Enkrypt · Harmful content risk 17.8%Enkrypt · CBRN risk 8.8%Enkrypt · Toxicity risk 2.2%Enkrypt · Bias risk 89.7%Enkrypt · Insecure code risk 50.2%

Vectara Hallucination Leaderboard ↗1 measureread 2026-11-10

Vectara · Factual consistency 91.8%

Badge

[![PublicAI Index](https://publicai.io/model-index/badge?model=llama-4-maverick-instruct)](https://publicai.io/model-index/m/llama-4-maverick-instruct)