Skip to content

Benchmarks

Sources
8
Entries tracked
22,318
Last sync
25 min
All sources syncing normally
  • Arena · Text2 hours ago
  • Arena · WebDev2 hours ago
  • Arena · Vision2 hours ago
  • Arena · Agent2 hours ago
  • GPQA Diamond25 minutes ago
  • SWE-bench25 minutes ago
  • Terminal-Bench25 minutes ago
  • ARC-AGI-225 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
431OpenHands + CodeAct v2.1 (claude-3-5-sonnet-20241022)———49.4 47.7Ranked 49.4 = (1 × 47.7 + 3 × 50) ÷ 4. 47.7 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—————————————————48—————
657claude-3-5-sonnet-20241022anthropicJun 2024—43.0 41.0Ranked 43.0 = (11 × 41.0 + 3 × 50) ÷ 14. 41.0 is the mean percentile over the 11 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.41–446111/22#126–65755—36————382522——73761—68—5748——

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.