GPT-5 Pro (2025-10-06)
Oct 2025
GPT-5 Pro (2025-10-06)Compare inon
GPT-5 Pro (2025-10-06) measured on 4 of 109 Chat & Knowledge benchmarks4
BenchmarkByScoreRank
Reasoning1
Math3
No benchmark matches
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperClaude Opus 4.8max×2.1-76%$4.08
OpenKimi K2.6unstatedsame-96%$0.95 / $4Context: 400K → 256KCheaperGPT-5.4 (2026-03-05)xhigh+86%-86%$2.50 / $15CheaperClaude Opus 4.7xhigh+57%-76%$5 / $25CheaperClaude Opus 4.6max+57%-76%$5 / $25ModelScoreCostPer taskWhat changes
Claude Opus 4.8max×2.1-76%$4.08GPT-5.4 (2026-03-05)xhigh+86%-86%$2.50 / $15Claude Opus 4.7xhigh+57%-76%$5 / $25Claude Opus 4.6max+57%-76%$5 / $25GPT-5.2 (2025-12-11)xhigh+29%-88%$1.75 / $14ModelScoreCostPer taskWhat changes
Claude Opus 4.8max×2.1-76%$4.08GPT-5.4 (2026-03-05)xhigh+86%-86%$2.50 / $15Claude Opus 4.7xhigh+57%-76%$5 / $25Claude Opus 4.6max+57%-76%$5 / $25GPT-5.2 (2025-12-11)xhigh+29%-88%$1.75 / $14ModelScoreCostPer taskWhat changes
Kimi K2.6unstatedOpensame-96%$0.95 / $4Context: 400K → 256K
GLM 5.1unstatedOpen-14%-95%$1.40 / $4.40Context: 400K → 203K+1GLM-4.6unstatedOpen-85%-98%$0.60 / $2.20Context: 400K → 200K+1GLM 5unstatedOpen-86%-96%$1 / $3.20Context: 400K → 203K+1Kimi K2 ThinkingunstatedOpen-100%-98%$0.47 / $2Context: 400K → 256K+1ModelScoreCostPer taskWhat changes
GPT-5.4 (2026-03-05)xhigh+86%—$2.50 / $15GPT-5.2 (2025-12-11)high+29%—$1.75 / $14GPT-5.1 (2025-11-13)high-14%—$1.25 / $10GPT-5 (2025-08-07)high-14%—$1.25 / $10GPT-5.4 Nano (2026-03-17)high-57%—$0.20 / $1.25GPT-5 Mini (2025-08-07)high-57%—$0.25 / $2o3 (2025-04-16)high-86%—$2 / $8Context: 400K → 200KGPT-5.4 Mini (2026-03-17)high-86%—$0.75 / $4.50All OpenAI models →Benchmarks
in Chat & KnowledgeFrontierMath Tier 414.6#7
FrontierMath Tiers 1–3 (v2)55.8#41
FrontierMath Tier 4 (v2)19.5#42
Chess Puzzles48#15
FAQ
How much does GPT-5 Pro (2025-10-06) cost?›
$15 per 1M input tokens and $120 per 1M output tokens.
Is GPT-5 Pro (2025-10-06) free to use?›
There is no free API; the cheapest paid price is $15 per 1M input tokens.
How good is GPT-5 Pro (2025-10-06), and what is it best at?›
#41 of 70 in Chat & Knowledge.
Is GPT-5 Pro (2025-10-06) better than Muse Spark?›
On FrontierMath Tier 4, GPT-5 Pro (2025-10-06) scores 14.6 vs 14.6 — about the same.
How can I use GPT-5 Pro (2025-10-06)?›
Through the OpenAI API.
What is the context window of GPT-5 Pro (2025-10-06)?›
400K tokens.
When was GPT-5 Pro (2025-10-06) released? Is there a newer version?›
Released 2025-10-06. It has been superseded by GPT-5.6 Sol.
Can GPT-5 Pro (2025-10-06) read images?›
It accepts text and images as input.
What is GPT-5 Pro (2025-10-06)?›
GPT-5 Pro (2025-10-06) is a language model from OpenAI, released Oct 2025.
What are the best alternatives to GPT-5 Pro (2025-10-06)?›
Claude Opus 4.8 (cheaper), Kimi K2.6 (open weights).