Skip to content

Benchmarks

Sources
8
Entries tracked
21,843
Last sync
59 min
All sources syncing normally
  • Arena · Text8 hours ago
  • Arena · WebDev3 hours ago
  • Arena · Vision8 hours ago
  • Arena · Agent3 hours ago
  • GPQA Diamond59 minutes ago
  • SWE-bench11 hours ago
  • Terminal-Bench11 hours 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) ×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
348Down 1 place since Oct 28 (was #347)Llama 3 1 405b InstructmetaJul 2024—34.3Ranked 34.3 = (4 × 22.4 + 3 × 50) ÷ 7. 22.4 is the Avg: the mean percentile over the 4 of 18 selected axes this model is measured on; fewer axes means a stronger pull toward 50.32–3522.4334/18#132–35346——————1913————13—————

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.