priorsBuilder

OpenAI · released 2026-02-05

GPT-5.3 Codex

Measured on 33 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. #63xhigh of 58742.5%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #90xhigh of 52610.9

Leader: Opus 5.5 · 46.4

reasoning

BullshitBench v2

196 results
  1. #135low of 19624.0%
  2. #141high of 19620.0%
  3. #148xhigh of 19619.0%

Leader: Opus 4.8 · 95.0%

All 33 benchmarks

show 30 more

agentic

AA-Briefcase v1.1

224 results
  1. #143xhigh of 224868

Leader: Sonnet 5.5 · 1823

agentic

Terminal-Bench 2.0

40 results
  1. #4xhigh of 4078.4%

Leader: GPT-5.5 · 84.7%

agentic

Vending-Bench 2

67 results
  1. #21xhigh of 67$5,940

Leader: GPT-6 Astra · $15,515

agentic

τ²-Bench Telecom

393 results
  1. #92xhigh of 39386.0%

Leader: GLM 5.2 · 99.1%

coding

Arena Image-to-WebDev

58 results
  1. #47xhigh of 581444

Leader: Opus 5.5 · 1749

coding

Arena WebDev

122 results
  1. #80xhigh of 1221409

Leader: Opus 5.5 · 1813

coding

IOI

44 results
  1. #22xhigh of 4453.8%

Leader: Gemini 4 · 100.0%

coding

LiveCodeBench (Vals)

127 results
  1. #16xhigh of 12787.3%

Leader: Fable 5.1 · 90.5%

coding

SWE-bench Verified (Vals)

85 results
  1. #32xhigh of 8578.0%

Leader: Opus 5 · 97.0%

coding

Terminal-Bench 2.0 (Vals)

63 results
  1. #6high of 6364.0%

Leader: GPT-5.5 · 73.2%

coding

Terminal-Bench Hard-AA

387 results
  1. #17xhigh of 38753.0%

Leader: GPT-5.6 Sol · 65.9%

coding

Vibe Code Bench v1.1

105 results
  1. #46xhigh of 10561.8%

Leader: Sonnet 5.5 · 92.4%

coding

WeirdML v2

127 results
  1. #20xhigh of 12777.9%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #106xhigh of 61032.5

Leader: Opus 5.5 · 57.6

creative

MineBench

72 results
  1. #30xhigh of 721613

Leader: GPT-6 Astra Pro · 2281

creative

threejseval

34 results
  1. #31high of 341169

Leader: Opus 5.5 · 2079

instruction

IFBench

399 results
  1. #33xhigh of 39975.4%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #50xhigh of 52652.9%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #387xhigh of 52610.8%

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

knowledge

GPQA Diamond

539 results
  1. #46xhigh of 53991.5%

Leader: GPT-6 Astra · 96.3%

knowledge

MMMU-Pro

265 results
  1. #69xhigh of 26578.5%

Leader: Opus 5.5 · 87.7%

long-context

AA-LCR v1.1

523 results
  1. #22xhigh of 52383.3%

Leader: Kimi K3 · 88.7%

other

T3 Code usage share

85 results
  1. #22xhigh of 850.0%

Leader: Opus 5.5 · 29.1%

reasoning

CritPt

529 results
  1. #81xhigh of 52916.9%

Leader: Muse Wonder Full (Max) · 32.9%

reliability

Tool-call error rate

171 results
  1. #11xhigh of 1710.1%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #28xhigh of 181100.0%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #324xhigh of 35170s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #132xhigh of 351113.1

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #152xhigh of 1773.5s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #82xhigh of 17668.5

Leader: Muse Spark 1.1 · 204.3