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 GPT-4o mini?

68 SI-IQ · 90% interval 64–73
Rank 79 of 80 ranked models · Plausible rank range 75–80

GPT-4o mini is a model from OpenAI, released on Jul 18, 2024. Its SI-IQ is 68 (90% interval 64–73), estimated from 10 benchmark results by 3 evaluators. Its strongest area is Reasoning and its weakest is Knowledge.

Data as of Oct 18, 2026 · method 1.0.0

Facts

Developer: OpenAI
Released: Jul 18, 2024
Access: API access
Benchmarks used: 10 benchmark results from 3 evaluators
API price: $0.15 input / $0.60 output per 1M tokens (developer's price list, Oct 18, 2026)
Context window: 128,000 tokens

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
Chess Puzzles	Reasoning	3.0%	61	Epoch AI	`gpt-4o-mini-2024-07-18`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
Mystery Game Puzzles	Reasoning	12.0%	96	Epoch AI	`gpt-4o-mini-2024-07-18`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
FrontierMath Tiers 1–3	Math	0.7%	72	Epoch AI	`gpt-4o-mini-2024-07-18`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
MATH Level 5	Math	52.6%	71	Epoch AI	`gpt-4o-mini-2024-07-18`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
OTIS Mock AIME 2024–2025	Math	6.9%	66	Epoch AI	`gpt-4o-mini-2024-07-18`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
Aider Polyglot	Coding	3.6%	50	Aider	`gpt-4o-mini-2024-07-18`	Oct 18, 2026	Aider LLM Leaderboards · data file
GPQA Diamond	Knowledge	37.7%	55	Epoch AI	`gpt-4o-mini-2024-07-18`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
GPQA Diamond (OpenRouter run)	Knowledge	43.1%	63	OpenRouter	`openai/gpt-4o-mini` OpenAI · first-party provider (1 of 2 rows)	Oct 18, 2026	OpenRouter benchmark datasets · data file
SimpleQA Verified	Knowledge	8.3%	71	Epoch AI	`gpt-4o-mini-2024-07-18`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
τ²-bench Airline (OpenRouter run)	Agents	28.0%	55	OpenRouter	`openai/gpt-4o-mini` OpenAI · first-party provider (1 of 1 rows)	Oct 18, 2026	OpenRouter benchmark datasets · data file

Human preference (Arena)

On the Arena leaderboard, where people vote between two anonymous answers, GPT-4o mini has a rating of 1,318 (1,314–1,321) from 68,705 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
GPT-4o (Nov 2024)OpenAI	69	GPT-4o mini vs GPT-4o (Nov 2024)
Llama 3.3 70BMeta AI	66	GPT-4o mini vs Llama 3.3 70B
GPT-4o (Aug 2024)OpenAI	73	GPT-4o mini vs GPT-4o (Aug 2024)
GPT-4.1 nanoOpenAI	76	GPT-4o mini vs GPT-4.1 nano
Gemma 3 27BGoogle DeepMind	77	GPT-4o mini vs Gemma 3 27B

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); Epoch AI, ‘Capabilities & benchmarking’ (CC BY 4.0); LiteLLM, model_prices_and_context_window.json (MIT); Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter (licences and changes).