Skip to content

Benchmarks

Sources
8
Entries tracked
22,308
Last sync
37 min
All sources syncing normally
  • Arena · Text37 minutes ago
  • Arena · WebDev37 minutes ago
  • Arena · Vision37 minutes ago
  • Arena · Agent37 minutes ago
  • GPQA Diamond1 hour ago
  • SWE-bench1 hour ago
  • Terminal-Bench1 hour ago
  • ARC-AGI-21 hour ago

gemini-3-flash-preview

72±1

70interval74

Google DeepMindswing #27–#99

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) ×13 of 1034 models
ModelOrgIntervalSwingiiiiiiiiiiiiiiiiiiiiiiAdd to compare
27gemini-3-flash-previewGoogle DeepMind—$0.50 / $372.3 78.4Ranked 72.3 = (11 × 78.4 + 3 × 50) ÷ 14. 78.4 is the mean percentile over the 11 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.70–748211/22#27–99———————7982818855—7589———991009718
153gemini-3-flashgoogleJan 2026—59.7 65.6Ranked 59.7 = (5 × 65.6 + 3 × 50) ÷ 8. 65.6 is the mean percentile over the 5 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.56–62705/22#38–15391528183—21————————————————
521gemini-3-flash-groundinggoogleOct 2026—47.0 38.1Ranked 47.0 = (1 × 38.1 + 3 × 50) ÷ 4. 38.1 is the mean percentile over the 1 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.45–49—1/22low—————38—————————————————

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.