Skip to content

Benchmarks

Sources
8
Entries tracked
22,308
Last sync
28 min
All sources syncing normally
  • Arena · Text29 minutes ago
  • Arena · WebDev29 minutes ago
  • Arena · Vision29 minutes ago
  • Arena · Agent28 minutes ago
  • GPQA Diamond52 minutes ago
  • SWE-bench52 minutes ago
  • Terminal-Bench52 minutes ago
  • ARC-AGI-252 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
791phi-3-mini-4k-instruct-june-2024microsoftJun 2024—39.8 9.1Ranked 39.8 = (1 × 9.1 + 3 × 50) ÷ 4. 9.1 is the mean percentile over the 1 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.39–41—1/22low#359–7919—————————————————————
968phi-3-mini-4k-instructmicrosoftApr 2024—33.2 7.9Ranked 33.2 = (2 × 7.9 + 3 × 50) ÷ 5. 7.9 is the mean percentile over the 2 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.32–3422/22low#364–9687—————————————9———————

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.