ModelTape
All modelsNew releasesRankingsRuns on my GPUOpen the app →
ModelTape / Models / GPT-5.4 Mini
OpenAI · API-only (closed weights)

GPT-5.4 Mini

GPT-5.4 Mini is an API-only (closed weights) language model from OpenAI, released March 17, 2026. The context window is 391K tokens. On the Epoch Capabilities Index it scores 149.3, rank 73 of 256 rated models. API price: $0.75 input / $4.5 output per million tokens.

Check it against your own PC →

Lab
OpenAI
Released
March 17, 2026
Weights
API-only (closed weights)
Parameters
–
Context
391K
Price / M tokens
$0.75 / $4.5 in / out
Epoch ECI
149.3 #73

Strengths by category

ModelTape's 0–100 fit on Epoch AI benchmark results.

CategoryScoreBased on
Reasoning13.4Chess Puzzles, Mystery Game Puzzles
Math38.6ProofBench, OTIS Mock AIME 2024-2025, FrontierMath-Tiers-1-3-v2-Private, FrontierMath-Tier-4-v2-Private
Knowledge67.9GPQA diamond, SimpleQA Verified

Benchmark results

Benchmark (Epoch AI)Score
OTIS Mock AIME88.9%
GPQA Diamond85.9%
FrontierMath (Tiers 1–3)53.9%
SimpleQA Verified29.4%
ProofBench21.0%
Chess Puzzles19.0%
FrontierMath-Tier-4-v2-Private9.8%
Mystery Game Puzzles2.0%

Links

Announcement · Epoch AI benchmarks

Models with a similar score

Muse Spark · GLM-5.2 · Gemini 3 Pro · Claude Sonnet 4.6 · Mistral Large 4 Preview · Qwen 3.8 27B · Gemini 3 Flash · Grok 4.20

More from OpenAI

GPT-6.1 Terra · GPT-6.1 Sol · GPT-6 Sol · GPT-6 Luna · GPT-6 Astra · GPT-5.6 Cyber · Daybreak Red · Daybreak Blue

Data updated Thu, 12 Nov 2026 09:42 UTC. Benchmarks, Capabilities Index and model announcements: Epoch AI, “Capabilities & benchmarking” and “Data on AI models” (CC BY 4.0); category scores are ModelTape's own fit on Epoch's results. Releases and prices: models.dev (MIT). Sizes and quantizations: Hugging Face. “Runs on” figures are estimates from model size, quantization and memory bandwidth (±30–50%).
Live app · All models · New releases · Rankings · 6 GB · 8 GB · 12 GB · 16 GB · 24 GB · 32 GB · Legal notice (Impressum) · Privacy