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-5.4 Mini?

117 SI-IQ · 90% interval 113–120
Rank 45 of 80 ranked models · Plausible rank range 34–60

GPT-5.4 Mini is a model from OpenAI, released on Mar 17, 2026. Its SI-IQ is 117 (90% interval 113–120), estimated from 8 benchmark results by 2 independent evaluators. Its strongest area is Math and its weakest is Reasoning.

Facts

Developer: OpenAI
Released: Mar 17, 2026
Access: API access
Benchmarks used: 8 results from 2 evaluators
API price: $0.75 input / $4.50 output per 1M tokens (developer's price list, Oct 18, 2026)
Context window: 272,000 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	23.0%	115	Epoch AI	`gpt-5.4-mini-2026-03-17_high`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
Mystery Game Puzzles	Reasoning	11.0%	91	Epoch AI	`gpt-5.4-mini-2026-03-17_none`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
FrontierMath Tier 4	Math	9.8%	117	Epoch AI	`gpt-5.4-mini-2026-03-17_xhigh`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
FrontierMath Tiers 1–3	Math	51.2%	120	Epoch AI	`gpt-5.4-mini-2026-03-17_xhigh`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
OTIS Mock AIME 2024–2025	Math	88.9%	115	Epoch AI	`gpt-5.4-mini-2026-03-17_xhigh`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
GPQA Diamond	Knowledge	86.9%	118	Epoch AI	`gpt-5.4-mini-2026-03-17_xhigh`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
GPQA Diamond (OpenRouter run)	Knowledge	84.0%	117	OpenRouter	`openai/gpt-5.4-mini-20260317` OpenAI · first-party provider (1 of 2 rows)	Oct 18, 2026	OpenRouter benchmark datasets · data file
SimpleQA Verified	Knowledge	29.4%	108	Epoch AI	`gpt-5.4-mini-2026-03-17_high`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
τ²-bench Airline (OpenRouter run)	Agents	62.2%	107	OpenRouter	`openai/gpt-5.4-mini-20260317` OpenAI · first-party provider (1 of 2 rows)	Oct 18, 2026	OpenRouter benchmark datasets · data file

Models with similar SI-IQ

Model	SI-IQ
DeepSeek-V4-ProDeepSeek	117	GPT-5.4 Mini vs DeepSeek-V4-Pro
o3OpenAI	116	GPT-5.4 Mini vs o3
GLM-5.1Z.ai (Zhipu AI)	116	GPT-5.4 Mini vs GLM-5.1
GPT-5.4 NanoOpenAI	118	GPT-5.4 Mini vs GPT-5.4 Nano
Inkling-SmallThinking Machines	118	GPT-5.4 Mini vs Inkling-Small

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

Data sources: 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..