Skip to content

Benchmarks

Sources
8
Entries tracked
22,308
Last sync
59 min
All sources syncing normally
  • Arena · Text11 hours ago
  • Arena · WebDev11 hours ago
  • Arena · Vision11 hours ago
  • Arena · Agent11 hours ago
  • GPQA Diamond60 minutes ago
  • SWE-bench59 minutes ago
  • Terminal-Bench59 minutes ago
  • ARC-AGI-259 minutes ago
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
243deepseek-r1-0528deepseekMay 2025$0.50 / $2.1556.3 58.4Ranked 56.3 = (9 × 58.4 + 3 × 50) ÷ 12. 58.4 is the mean percentile over the 9 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.55–58729/22#88–25070——————5747——19—3480———918740—
919deepseek-r1-0528-qwen3-8bdeepseek——36.7 28.7Ranked 36.7 = (5 × 28.7 + 3 × 50) ÷ 8. 28.7 is the mean percentile over the 5 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.36–37565/22#465–919———————036—————————48572—

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.