Skip to content

Benchmarks

Sources
8
Entries tracked
22,310
Last sync
28 min
All sources syncing normally
  • Arena · Text5 hours ago
  • Arena · WebDev5 hours ago
  • Arena · Vision5 hours ago
  • Arena · Agent5 hours ago
  • GPQA Diamond28 minutes ago
  • SWE-bench28 minutes ago
  • Terminal-Bench28 minutes ago
  • ARC-AGI-228 minutes ago

GLM-4.5-AIR-FP8

52±0

51interval52

zai-orgswing #374–#374

glm-4.5-air

50±1

48interval51

zaiJul 2025swing #138–#416

Overall ×1WebDev Arena ×1Vision Arena ×1Factuality Arena ×1Search Arena ×1Document Arena ×1Agent Arena ×1GPQA Diamond ×1AIME (math) ×1FrontierMath ×1SimpleQA Verified ×1ARC-AGI-2 ×1Humanity's Last Exam ×1SimpleBench ×1LiveBench ×1BFCL v4 (function calling) ×1dormantSWE-bench Verified (live board) ×1Terminal-Bench 4.0 ×1MMLU-Pro (Artificial Analysis) ×1LiveCodeBench (Artificial Analysis) ×1IFBench (Artificial Analysis) ×1HHEM Hallucination (Vectara) ×12 of 1034 models
ModelOrgIntervalSwingiiiiiiiiiiiiiiiiiiiiiiAdd to compare
374GLM-4.5-AIR-FP8zai-org——51.5 56.2Ranked 51.5 = (1 × 56.2 + 3 × 50) ÷ 4. 56.2 is the mean percentile over the 1 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.——1/22low——————————————————————56
416glm-4.5-airzaiJul 2025$0.13 / $0.8550.0 50.0Ranked 50.0 = (7 × 50.0 + 3 × 50) ÷ 10. 50.0 is the mean percentile over the 7 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.48–51607/22#138–41655——16————————33—64———757434—

Blend is coverage-shrunk; the raw composite is shown greyed beside it · A low badge means fewer than 3 boards scored this model

The few things in AI and quantum that actually mattered this week — honestly summarised.

One email a week. Unsubscribe in one click. No tracking, no sharing.