GPT-5 Pro

+ contribute

GPT-5 Pro is a closed-weights language model from OpenAI, released October 2025. Licence: proprietary.

Catalogue identity notes

Comparison model from the Epoch AI internal-evaluation CSVs (Epoch release date 2025-10-07). Epoch label gpt-5-pro-2025-10-06 (default and only snapshot). Distinct from gpt-5 and later Pro models. OpenAI deprecations page schedules shutdown for December 11, 2026.

72.8±0.9#58 of 719 LLMsfrom 7 benchmark results across 3 sources

$ how it compares

The LLMs ranked either side of GPT-5 Pro, out of 828 with a score, then more from OpenAI.

#	model	score	where	RAM	released
60	Grok 4.20 Multi-Agent (0309) SpaceXAI (xAI)	73±2	api $1.56/M		2026-03
61	Kimi K2.6 Moonshot AI	73±1	api $1.71/M +local	~317GB	2026-04
62	GPT-5 Pro OpenAI	73±1	api $41.25/M		2025-10
63	LongCat 2.0 (1.6T-A48B) Meituan	73±2	api $1.30/M +local	~2155GB	2026-06
64	Gemini 3 Pro (Preview) Google	73±1	comparison only		2025-11
	more from OpenAI
1	GPT-6 Astra OpenAI	87±1	api $20.00/M		2026-09
3	GPT-6.1 Sol OpenAI	85±1	api $4.00/M		2026-09
7	GPT-6 Sol OpenAI	83±1	api $4.00/M		2026-09

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▆▅▅▅▄▃▁ #74 of 300 * · 5.1% of its score · 1 test

Trails MiMo-V2.5 (310B-A15B), Qwen3.6 27B, Muse Glimmer 30B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Humanity's Last Exam with tools lab	42.0% ✎	▃·▃·▅····▅·█ beats 3/8	very hard · avg 12%	▇▇ 5.1%	at its level

math▁▂▃▅▆▅▄█▄▁▁▁ #47 of 398 * · 63% of its score · 2 tests

Beats Grok 4.7, GLM-5.3-Flash here, though they rank higher overall. Trails A.X K2 (688B-A33B), DeepSeek V4 Flash (Preview, Apr 2026), GPT-5 here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
FrontierMath tiers 1–3 v2	55.8% ✎	▂··▁▁▃▄▄█▅▃▃ beats 40/82	very hard · avg 1.2%	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 39%	sharp · at its level
FrontierMath tier 4 v2	19.5% ✎	▁▂▁▂█▅▂▂▁▁▁▁ beats 21/63	very hard · avg 0.1%	▇▇▇▇▇▇▇▇▇ 24%	sharp

web search▂▁▂▆▄█▃▃▁▁·▁ #57 of 80 * · 5.1% of its score · 1 test

Trails GPT-4o mini (2024-07-18), Mistral Small 3.1 24B (2503), Llama 4 Scout (109B-A17B) here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Humanity's Last Exam with tools lab	42.0% ✎	▃·▃·▅····▅·█ beats 3/8	very hard · avg 12%	▇▇ 5.1%	at its level

other tests4 not in a task · 32% of its score

test	result	vs the others in its run	difficulty	counts	why
GPQA Diamond lab	88.4% ✎	▁▁▁▁▂▄▅▅███▄ beats 254/310	hard · avg 39%	▇▇▇▇ 10%	sharp
ARC-AGI-2 public evaluation set (ARC Prize model_baseline, pass@2)	13.3% ✎	█··▂▅▁▃▁▃·▁▃ beats 14/24	very hard · avg 0.3%	▇▇▇▇ 8.8%	sharp · at its level · noisy
Humanity's Last Exam lab	30.7% ✎	▃··▃·▃▃···▃█ beats 3/7	very hard · avg 4.4%	▇▇▇ 8.1%	at its level
ARC-AGI-1 public evaluation set (ARC Prize model_baseline, pass@2)	77.0% ✎	▁·▇▃▁·█▇▁·▇▃ beats 18/27	very hard · avg 4.1%	▇▇ 4.6%	sharp · noisy

$ where to run it

Through an API

api · $41.25/M · $15 in / $120 out per 1M tokens · 400k context · developers.openai.com ↗ · price sourceUSD per 1M tokens, OpenAI API standard processing, model page 'gpt-5-pro' whose default snapshot is gpt-5-pro-2025-10-06: input $15, output $120; cached-input, Batch and other tiers excluded. Currency: USD. OpenAI official model page, observed 2026-09-28.

$ how the score was worked out · Epoch AI — internal evaluatio… 63%, OpenAI vendor-reported benchm… 24%, ARC Prize Foundation model_ba… 13%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

source	results	share of the score	licence
Epoch AI — internal evaluations	2	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 63%	CC BY 4.0
OpenAI vendor-reported benchmark scores for its own models (openai.com announcement posts and Deployment Safety Hub system cards) · lab-reported	3	▇▇▇▇▇▇▇ 24%	Factual vendor-reported score (not licensed content)
ARC Prize Foundation model_baseline outputs on ARC-AGI-1/2 public evaluation sets	2	▇▇▇▇ 13%	MIT
prior · pull toward the middle		▇ 0%
weighted average		= 72.8

$ improve this page

Update model information Add a place to run it Add a test result Propose a benchmark Correct a benchmark score Edit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated 2026-10-11 02:20 UTC · sources and licences · json