priorsBuilder

OpenAI · released 2025-09-23

GPT-5 Codex

Measured on 24 benchmarks.

General frontier

Not ranked in this mix — too little measured data for its benchmarks.

Your mix’s benchmarks

3 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #168high of 58727.8%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #170high of 526-7.5

Leader: Opus 5.5 · 46.4

reasoning

BullshitBench v2

196 results
  1. #99medium of 19639.0%

Leader: Opus 4.8 · 95.0%

All 24 benchmarks

show 21 more

agentic

Terminal-Bench 2.0

40 results
  1. #20high of 4044.3%

Leader: GPT-5.5 · 84.7%

agentic

τ²-Bench Telecom

393 results
  1. #83high of 39386.8%

Leader: GLM 5.2 · 99.1%

coding

LiveCodeBench

282 results
  1. #16high of 28284.0%

Leader: Gemini 3 Pro · 91.7%

coding

LiveCodeBench (Vals)

127 results
  1. #37high of 12784.7%

Leader: Fable 5.1 · 90.5%

coding

Terminal-Bench Hard-AA

387 results
  1. #63high of 38737.9%

Leader: GPT-5.6 Sol · 65.9%

coding

WeirdML v2

127 results
  1. #53high of 12754.5%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #163high of 61024.9

Leader: Opus 5.5 · 57.6

creative

VoxelBench (image)

16 results
  1. #12high of 161175

Leader: GPT-6.1 Sol · 2204

creative

VoxelBench (text)

55 results
  1. #48high of 551271

Leader: GPT-6 Astra · 2733

instruction

IFBench

399 results
  1. #36high of 39974.1%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #129high of 52638.7%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #242high of 52624.6%

Leader: MiniCPM5-1B (Non-reasoning) · 99.1%

knowledge

GPQA Diamond

539 results
  1. #155high of 53983.7%

Leader: GPT-6 Astra · 96.3%

knowledge

MMLU-Pro

285 results
  1. #16high of 28586.5%

Leader: Gemini 3 Pro · 89.8%

knowledge

MMMU-Pro

265 results
  1. #115high of 26573.8%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #195high of 52371.7%

Leader: Kimi K3 · 88.7%

math

AIME 2025

228 results
  1. #2high of 22898.7%

Leader: GPT-5.2 · 99.0%

other

T3 Code usage share

85 results
  1. #21high of 850.0%

Leader: Opus 5.5 · 29.1%

reasoning

CritPt

529 results
  1. #151high of 5295.1%

Leader: Muse Wonder Full (Max) · 32.9%

speed

Latency (Time to First Token)

351 results
  1. #249high of 35110s

Leader: Gemini 2.5 Flash Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #56high of 351188.0

Leader: Celeris-1 · 1564.1