Automated page. Written and translated automatically by AI and checked against the sources by software; no human editor. SI-IQ is an index built from public benchmark results, not an IQ test. How it works

How smart is Llama 4 Maverick?

81 SI-IQ · 90% interval 77–85
Rank 74 of 80 ranked models · Plausible rank range 74–77

Llama 4 Maverick is a model from Meta AI, released on Apr 5, 2025. Its SI-IQ is 81 (90% interval 77–85), estimated from 6 benchmark results by 4 independent evaluators. Its strongest area is Agents and its weakest is Math.

Facts

Developer: Meta AI
Released: Apr 5, 2025
Access: Open weights (restricted licence)
Benchmarks used: 6 results from 4 evaluators

Ability by area (SI-IQ, 90% interval)

Every benchmark result we used

Each score is one value exactly as the source published it: for Epoch AI the best of its run settings, for OpenRouter the median hosting provider (the developer's own hosting when it ran the test). “Implied SI-IQ” is the ability that this single result points to; the overall SI-IQ is their precision-weighted average.

Benchmark	Area	Score	Implied SI-IQ	Evaluated by	As listed by the source	Retrieved	Source
MATH Level 5	Math	73.0%	81	Epoch AI	`Llama-4-Maverick-17B-128E-Instruct-FP8`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
OTIS Mock AIME 2024–2025	Math	20.6%	79	Epoch AI	`Llama-4-Maverick-17B-128E-Instruct-FP8`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
Aider Polyglot	Coding	15.6%	72	Aider	`Llama 4 Maverick`	Oct 18, 2026	Aider LLM Leaderboards · data file
GPQA Diamond	Knowledge	67.0%	92	Epoch AI	`Llama-4-Maverick-17B-128E-Instruct-FP8`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
GPQA Diamond (OpenRouter run)	Knowledge	64.8%	91	OpenRouter	`meta-llama/llama-4-maverick-17b-128e-instruct` DeepInfra · median over providers (4 of 4 rows), lower median	Oct 18, 2026	OpenRouter benchmark datasets · data file
Berkeley Function Calling Leaderboard	Agents	37.3%	81	UC Berkeley (Gorilla)	`Llama-4-Maverick-17B-128E-Instruct-FP8 (FC)`	Oct 18, 2026	Berkeley Function Calling Leaderboard · data file
τ²-bench Airline (OpenRouter run)	Agents	43.1%	79	OpenRouter	`meta-llama/llama-4-maverick-17b-128e-instruct` Parasail · median over providers (2 of 2 rows), lower median	Oct 18, 2026	OpenRouter benchmark datasets · data file

Human preference (Arena)

On the Arena leaderboard, where people vote between two anonymous answers, Llama 4 Maverick has a rating of 1,327 (1,323–1,331) from 39,450 votes (published Oct 15, 2026). Human preference is a different measure from benchmark ability and is not part of SI-IQ. Arena (Hugging Face)

Models with similar SI-IQ

Model	SI-IQ
Gemma 3 27BGoogle DeepMind	77	Llama 4 Maverick vs Gemma 3 27B
GPT-4.1 nanoOpenAI	76	Llama 4 Maverick vs GPT-4.1 nano
GPT-4o (Aug 2024)OpenAI	73	Llama 4 Maverick vs GPT-4o (Aug 2024)
GPT-4.1OpenAI	91	Llama 4 Maverick vs GPT-4.1
GPT-4.1 miniOpenAI	91	Llama 4 Maverick vs GPT-4.1 mini

Computed with SI-IQ method version 1.0.0. Read the full methodology

Data sources: Aider polyglot leaderboard data (Apache-2.0); Arena leaderboard dataset on Hugging Face (CC BY 4.0); Berkeley Function Calling Leaderboard, Gorilla project (Apache-2.0); Epoch AI, ‘Capabilities & benchmarking’ (CC BY 4.0); Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter..