priorsBuilder

Alibaba · released 2024-09-19

Qwen 2.5 72B

Measured on 23 benchmarks.

General frontier

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

Your mix’s benchmarks

2 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #566none of 5873.6%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #395none of 526-53.1

Leader: Opus 5.5 · 46.4

All 23 benchmarks

show 21 more

agentic

τ²-Bench Telecom

393 results
  1. #240none of 39334.5%

Leader: GLM 5.2 · 99.1%

coding

LiveCodeBench

282 results
  1. #197none of 28227.6%

Leader: Gemini 3 Pro · 91.7%

coding

Terminal-Bench Hard-AA

387 results
  1. #272none of 3874.5%

Leader: GPT-5.6 Sol · 65.9%

coding

WeirdML v2

127 results
  1. #120none of 12716.0%

Leader: GPT-6 Astra Pro · 93.6%

composite

AA Intelligence Index v4.3.2

610 results
  1. #441none of 6107.7

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #186none of 2201303

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #179none of 2201299

Leader: Gemini 4 · 1553

instruction

IFBench

399 results
  1. #284none of 39936.9%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #347none of 52617.5%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #339none of 52614.5%

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

knowledge

GPQA Diamond

539 results
  1. #418none of 53949.1%

Leader: GPT-6 Astra · 96.3%

knowledge

MMLU-Pro

285 results
  1. #167none of 28572.0%

Leader: Gemini 3 Pro · 89.8%

math

AIME 2025

228 results
  1. #186none of 22814.0%

Leader: GPT-5.2 · 99.0%

math

MATH-500

162 results
  1. #73none of 16285.8%

Leader: GPT-5 · 99.4%

reasoning

CritPt

529 results
  1. #427none of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%

reliability

Tool-call error rate

171 results
  1. #146none of 1715.2%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #100none of 18199.3%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #219none of 3513.7s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #339none of 35131.2

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #6none of 1770.4s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #158none of 17632.0

Leader: Muse Spark 1.1 · 204.3