Skip to content

Benchmarks

Sources
8
Entries tracked
21,845
Last sync
23 min
All sources syncing normally
  • Arena · Text58 minutes ago
  • Arena · WebDev9 hours ago
  • Arena · Vision58 minutes ago
  • Arena · Agent9 hours ago
  • GPQA Diamond23 minutes ago
  • SWE-bench5 hours ago
  • Terminal-Bench5 hours ago
  • ARC-AGI-223 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) ×0dormantSWE-bench Verified (live board) ×1Terminal-Bench 4.0 ×1HHEM Hallucination (Vectara) ×11 of 367 models

289 models that are not available today are left out of this ranking.

ModelOrgIntervalSwingiiiiiiiiiiiiiiiiiiiAdd to compare
81Up 11 places since Oct 28 (was #92)Nvidia Nemotron 3 Ultra 550b A55bnvidia≈Oct 2026—52.6Ranked 52.6 = (2 × 56.6 + 3 × 50) ÷ 5. 56.6 is the Avg: the mean percentile over the 2 of 18 selected axes this model is measured on; fewer axes means a stronger pull toward 50.50–5556.6322/18low#49–8873——41———————————————

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.