priorsBuilder

Zhipu · released 2025-07-28

GLM 4.5 Air

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. #360default of 5877.0%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #448default of 526-61.5

Leader: Opus 5.5 · 46.4

All 23 benchmarks

show 21 more

agentic

τ²-Bench Telecom

393 results
  1. #212default of 39346.5%

Leader: GLM 5.2 · 99.1%

coding

LiveCodeBench

282 results
  1. #73default of 28268.4%

Leader: Gemini 3 Pro · 91.7%

coding

Terminal-Bench Hard-AA

387 results
  1. #166default of 38720.5%

Leader: GPT-5.6 Sol · 65.9%

composite

AA Intelligence Index v4.3.2

610 results
  1. #352default of 61011.1

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #141default of 2201373

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #142default of 2201368

Leader: Gemini 4 · 1553

instruction

IFBench

399 results
  1. #279default of 39937.6%

Leader: Grok 4.3 · 83.3%

knowledge

AA-Omniscience Accuracy

526 results
  1. #375default of 52616.3%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #467default of 5267.1%

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

knowledge

GPQA Diamond

539 results
  1. #264default of 53973.3%

Leader: GPT-6 Astra · 96.3%

knowledge

MMLU-Pro

285 results
  1. #72default of 28581.5%

Leader: Gemini 3 Pro · 89.8%

long-context

AA-LCR v1.1

523 results
  1. #316default of 52346.7%

Leader: Kimi K3 · 88.7%

math

AIME 2025

228 results
  1. #56default of 22880.7%

Leader: GPT-5.2 · 99.0%

math

MATH-500

162 results
  1. #27default of 16296.5%

Leader: GPT-5 · 99.4%

reasoning

CritPt

529 results
  1. #370default of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%

reliability

Tool-call error rate

171 results
  1. #50default of 1710.6%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #148default of 18198.1%

Leader: GPT-5 Pro · 100.0%

speed

Latency (Time to First Token)

351 results
  1. #178default of 3512.4s

Leader: Gemini 2.5 Flash-Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #210default of 35177.6

Leader: Celeris-1 · 1522.5

speed

Provider latency

177 results
  1. #72default of 1771.1s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #102default of 17655.0

Leader: Muse Spark 1.1 · 204.3