Skip to content

Benchmarks

Sources
8
Entries tracked
22,308
Last sync
35 min
All sources syncing normally
  • Arena · Text35 minutes ago
  • Arena · WebDev35 minutes ago
  • Arena · Vision35 minutes ago
  • Arena · Agent35 minutes ago
  • GPQA Diamond59 minutes ago
  • SWE-bench59 minutes ago
  • Terminal-Bench59 minutes ago
  • ARC-AGI-259 minutes ago

glm-5.2-max

68±2

65interval70

zaiJun 2026swing #9–#49

glm-5.1

68±2

65interval70

zaiApr 2026swing #44–#75

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) ×17 of 1034 models
ModelOrgIntervalSwingiiiiiiiiiiiiiiiiiiiiiiAdd to compare
45glm-5.2-maxzaiJun 2026$0.62 / $2.4267.9 72.8Ranked 67.9 = (11 × 72.8 + 3 × 50) ÷ 14. 72.8 is the mean percentile over the 11 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.65–705911/22#9–499383—79——608964—3453—6889—————89—
46glm-5.1zaiApr 2026$0.97 / $3.0467.9 73.2Ranked 67.9 = (10 × 73.2 + 3 × 50) ÷ 13. 73.2 is the mean percentile over the 10 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.65–706110/22#44–758863—73———81778033——6083—————94—
50glm-5.3-flashzaiAug 2026$0.05 / $0.2067.7 73.6Ranked 67.7 = (9 × 73.6 + 3 × 50) ÷ 12. 73.6 is the mean percentile over the 9 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.65–71519/22#26–6091838280——408278——74—————52————
52glm-5.3-maxzaiAug 2026$0.08 / $1.4067.3 73.8Ranked 67.3 = (8 × 73.8 + 3 × 50) ÷ 11. 73.8 is the mean percentile over the 8 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.63–70498/22#18–529486—82——588673—45——————65————
147glm-5zaiFeb 2026$1 / $3.2059.9 62.7Ranked 59.9 = (11 × 62.7 + 3 × 50) ÷ 14. 62.7 is the mean percentile over the 11 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.58–625211/22#57–1538648—67———755754—35—5779—————8645
158GLM-5-Turbozai—$1.20 / $459.6 88.3Ranked 59.6 = (1 × 88.3 + 3 × 50) ÷ 4. 88.3 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—————————————————————88—
435glm-5v-turbozaiSep 2026$1.20 / $449.4 49.1Ranked 49.4 = (7 × 49.1 + 3 × 50) ÷ 10. 49.1 is the mean percentile over the 7 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.47–51737/22#86–43576405952—3————————44—————70—

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.