priorsBuilder

OpenAI · released 2024-04-09

GPT-4

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. #577none of 5873.1%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #286none of 526-33.8

Leader: Opus 5.5 · 46.4

reasoning

SimpleBench

97 results
  1. #83high of 9725.1%

Leader: Opus 5.5 · 88.4%

All 26 benchmarks

show 23 more

coding

LiveCodeBench

282 results
  1. #188none of 28229.1%

Leader: Gemini 3 Pro · 91.7%

coding

WeirdML v2

127 results
  1. #119high of 12718.0%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #477none of 6107.0

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #169high of 2201324

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #175high of 2201313

Leader: Gemini 4 · 1553

economics

GDPval-AA v2.1

288 results
  1. #264none of 288-20

Leader: Opus 5.5 · 1866

instruction

IFBench

399 results
  1. #317none of 39933.2%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #280none of 52621.0%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #214none of 52630.6%

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

knowledge

GPQA Diamond

539 results
  1. #474none of 53934.9%

Leader: GPT-6 Astra · 96.3%

knowledge

MedQA (Vals)

80 results
  1. #59high of 8082.0%

Leader: o1 · 96.5%

knowledge

MMLU-Pro

285 results
  1. #184none of 28569.4%

Leader: Gemini 3 Pro · 89.8%

math

FrontierMath Tiers 1–3 (v2)

115 results
  1. #113high of 1150.7%

Leader: GPT-6.1 Sol · 93.7%

math

MATH-500

162 results
  1. #106none of 16273.7%

Leader: GPT-5 · 99.4%

other

Arena Vision

116 results
  1. #107high of 1161112

Leader: Fable 5 · 1308

other

T3 Code usage share

85 results
  1. #79high of 850.0%

Leader: Opus 5.5 · 29.1%

reasoning

LegalBench

135 results
  1. #81high of 13580.5%

Leader: Fable 5 · 88.6%

reliability

Tool-call error rate

172 results
  1. #69high of 1720.9%

Leader: Gemini 4 · 0.0%

reliability

Uptime (7d)

182 results
  1. #36high of 18299.9%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #204none of 3513.0s

Leader: Gemini 2.5 Flash Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #338none of 35132.6

Leader: Celeris-1 · 1564.1

speed

Provider latency

178 results
  1. #49high of 1780.9s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #80high of 17669.8

Leader: Muse Spark 1.1 · 204.5