Skip to content

Benchmarks

Sources
8
Entries tracked
22,310
Last sync
31 min
All sources syncing normally
  • Arena · Text6 hours ago
  • Arena · WebDev6 hours ago
  • Arena · Vision6 hours ago
  • Arena · Agent6 hours ago
  • GPQA Diamond31 minutes ago
  • SWE-bench31 minutes ago
  • Terminal-Bench31 minutes ago
  • ARC-AGI-231 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) ×16 of 1034 models
ModelOrgIntervalSwingiiiiiiiiiiiiiiiiiiiiiiAdd to compare
47DeepSeek-V3.2-SpecialeDeepSeek——67.8 78.4Ranked 67.8 = (5 × 78.4 + 3 × 50) ÷ 8. 78.4 is the mean percentile over the 5 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.—455/22——————————————5470———969973—
86deepseek-v3.2deepseekDec 2025$0.28 / $0.4263.7 69.5Ranked 63.7 = (7 × 69.5 + 3 × 50) ÷ 10. 69.5 is the mean percentile over the 7 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.62–65677/22#86–2477229—48——————————————95977075
92deepseek-v3.2-expdeepseekSep 2025$0.27 / $0.4162.9 67.2Ranked 62.9 = (9 × 67.2 + 3 × 50) ÷ 12. 67.2 is the mean percentile over the 9 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.61–64769/22#92–3347116—47——————————5587——91906287
180deepseek-v3.2-exp-thinkingdeepseekOct 2026—58.6 67.1Ranked 58.6 = (3 × 67.1 + 3 × 50) ÷ 6. 67.1 is the mean percentile over the 3 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.55–62123/22#77–18072——60——————————68———————
344deepseek-v3.2-thinkingdeepseekOct 2026—52.4 54.2Ranked 52.4 = (4 × 54.2 + 3 × 50) ÷ 7. 54.2 is the mean percentile over the 4 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.51–54474/22#103–3447129—41——————————76———————
583deepseek/deepseek-v3.2DeepSeek——44.8 29.2Ranked 44.8 = (1 × 29.2 + 3 × 50) ÷ 4. 29.2 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#76–583———————————29——————————

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.