modelbenchmark.io

gpt-4-5

OpenAI · gpt-4-5

Compare

Specification

most-agreed values

Context
128K
Max output
16K
Released
Knowledge cutoff
Retires
Open weights
Input
Output

Price

US dollars per million tokens · most-agreed

Input
$75.00
Output
$150.00
Cache read
$37.50

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Batch inputazure$37.50
Batch outputazure$75.00

Batch input is 50% below the interactive input price at the same listing.

Quality

4 benchmarks · 2 sources

Composite
62nd
percentile of 334 scored models
Rank
128 / 334
±0.05 sd
Evidence
4 × 2
3 or more benchmarks, from 2 or more sources
Effort range
one configuration only
coding39th1/3 bench
reasoning70th1/4 bench
math65th2/7 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
MATH level 578.6 ±1.1defaultEpoch AI2025-02-28
GPQA diamond68.7 ±3.3defaultEpoch AI2025-02-28
Aider polyglot44.9default · aider diffAider2025-02-27
OTIS Mock AIME 2024-202537.8 ±7.3defaultEpoch AI2025-02-28

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
azure$75.00$150.00$37.50128K16K

More from OpenAI

most-hosted first