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-4.1 mini?

91 SI-IQ · 90% interval 88–95
Rank 72 of 80 ranked models · Plausible rank range 68–73

GPT-4.1 mini is a model from OpenAI, released on Apr 14, 2025. Its SI-IQ is 91 (90% interval 88–95), estimated from 10 benchmark results by 4 independent evaluators. Its strongest area is Math and its weakest is Knowledge.

Facts

Developer: OpenAI
Released: Apr 14, 2025
Access: API access
Benchmarks used: 10 results from 4 evaluators
API price: $0.40 input / $1.60 output per 1M tokens (developer's price list, Oct 18, 2026)
Context window: 1,047,576 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	1.0%	61	Epoch AI	`gpt-4.1-mini-2025-04-14`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
Mystery Game Puzzles	Reasoning	7.0%	70	Epoch AI	`gpt-4.1-mini-2025-04-14`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
FrontierMath Tiers 1–3	Math	6.7%	93	Epoch AI	`gpt-4.1-mini-2025-04-14`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
MATH Level 5	Math	87.3%	92	Epoch AI	`gpt-4.1-mini-2025-04-14`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
OTIS Mock AIME 2024–2025	Math	44.7%	91	Epoch AI	`gpt-4.1-mini-2025-04-14`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
Aider Polyglot	Coding	32.4%	86	Aider	`gpt-4.1-mini`	Oct 18, 2026	Aider LLM Leaderboards · data file
GPQA Diamond	Knowledge	65.8%	90	Epoch AI	`gpt-4.1-mini-2025-04-14`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
GPQA Diamond (OpenRouter run)	Knowledge	64.7%	91	OpenRouter	`openai/gpt-4.1-mini-2025-04-14` OpenAI · first-party provider (1 of 2 rows)	Oct 18, 2026	OpenRouter benchmark datasets · data file
SimpleQA Verified	Knowledge	12.7%	83	Epoch AI	`gpt-4.1-mini-2025-04-14`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
Berkeley Function Calling Leaderboard	Agents	50.5%	98	UC Berkeley (Gorilla)	`GPT-4.1-mini-2025-04-14 (FC)`	Oct 18, 2026	Berkeley Function Calling Leaderboard · data file
τ²-bench Airline (OpenRouter run)	Agents	44.3%	81	OpenRouter	`openai/gpt-4.1-mini-2025-04-14` OpenAI · first-party provider (1 of 2 rows)	Oct 18, 2026	OpenRouter benchmark datasets · data file

Human preference (Arena)

On the Arena leaderboard, where people vote between two anonymous answers, GPT-4.1 mini has a rating of 1,383 (1,379–1,387) from 38,709 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-4.1OpenAI	91	GPT-4.1 mini vs GPT-4.1
Qwen3-32BAlibaba	95	GPT-4.1 mini vs Qwen3-32B
Claude Sonnet 4Anthropic	97	GPT-4.1 mini vs Claude Sonnet 4
Claude Opus 4Anthropic	98	GPT-4.1 mini vs Claude Opus 4
Claude 3.7 SonnetAnthropic	99	GPT-4.1 mini vs Claude 3.7 Sonnet

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); API list prices via LiteLLM's price table (MIT); each price links to the developer's pricing page; Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter..