priorsBuilder

OpenAI · released 2025-12-11

GPT-5.2 Codex

Measured on 26 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. #111xhigh of 58735.7%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #144xhigh of 526-2.2

Leader: Opus 5.5 · 46.4

reasoning

BullshitBench v2

196 results
  1. #90low of 19645.0%
  2. #100xhigh of 19639.0%
  3. #106high of 19637.0%

Leader: Opus 4.8 · 95.0%

All 26 benchmarks

show 23 more

agentic

Terminal-Bench 2.0

40 results
  1. #7xhigh of 4066.5%

Leader: GPT-5.5 · 84.7%

agentic

τ²-Bench Telecom

393 results
  1. #53xhigh of 39392.1%

Leader: GLM 5.2 · 99.1%

coding

Arena WebDev

122 results
  1. #102xhigh of 1221339

Leader: Opus 5.5 · 1813

coding

LiveCodeBench (Vals)

127 results
  1. #9xhigh of 12788.0%

Leader: Fable 5.1 · 90.5%

coding

SWE-bench Verified (Vals)

85 results
  1. #52high of 8572.4%

Leader: Opus 5 · 97.0%

coding

Terminal-Bench Hard-AA

387 results
  1. #69xhigh of 38737.1%

Leader: GPT-5.6 Sol · 65.9%

coding

Vibe Code Bench v1.1

105 results
  1. #59high of 10537.9%

Leader: Sonnet 5.5 · 92.4%

composite

AA Intelligence Index v4.3.2

610 results
  1. #129xhigh of 61028.5

Leader: Opus 5.5 · 57.6

creative

MineBench

72 results
  1. #61xhigh of 721100

Leader: GPT-6 Astra Pro · 2281

instruction

IFBench

399 results
  1. #16xhigh of 39977.6%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #114xhigh of 52641.1%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #226xhigh of 52626.6%

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

knowledge

GPQA Diamond

539 results
  1. #66xhigh of 53989.9%

Leader: GPT-6 Astra · 96.3%

knowledge

MMMU-Pro

265 results
  1. #88xhigh of 26576.3%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #43xhigh of 52382.3%

Leader: Kimi K3 · 88.7%

other

T3 Code usage share

85 results
  1. #50xhigh of 850.0%

Leader: Opus 5.5 · 29.1%

reasoning

CritPt

529 results
  1. #126xhigh of 5298.7%

Leader: Muse Wonder Full (Max) · 32.9%

reliability

Tool-call error rate

171 results
  1. #67xhigh of 1710.9%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #20xhigh of 181100.0%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #333xhigh of 351117s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #118xhigh of 351124.0

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #146xhigh of 1773.0s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #127xhigh of 17647.3

Leader: Muse Spark 1.1 · 204.3