GPT-4.5 (Preview)
Context 128K tokens
Providers
No provider publishes an API price for this model yet, so no cost can be modeled.
Composite
1 of 7 inputs6 radar axes: DesignArena's two boards share one9.4
Thin data · 1/7Based on only 1 of 7 Composite inputs — treat this rank as uncertaindominance-adjusted from 13.1: a better-measured model that is at least as good on each of these inputs ranks above it
AA Coding v4.x —Coding Agent v1.4 —AA Intelligence (est.) 4.4AA Agentic —Epoch ECI —Software ECI —DesignArena —/—
Radar: percentile among all models measured on each input; a gap means not measured.
Benchmark sheet
2 of 319 registered benchmark versions · bars show the percentile among all models measured on each benchmark.
Vision
CharXiv Reasoning val-v1.07955.4%
CharXiv Reasoning val-v1.0 → · validation — Can a multimodal model reason over the real, messy charts in scientific papers — combining values, trends and labels across a figure — rather than read off templated plots?
Writing
EQ-Bench Creative Writing v3471,259 Elo
EQ-Bench Creative Writing v3 v3 → · Published board — A LLM-judged creative writing benchmark with vocabulary and GPT-slop controls.
Missing coverage · 317 benchmark versions
No result does not mean a zero, or that the model was never tested. Collection failures and disputed versions retain their distinct status.