Skip to content

Benchmarks

Sources
8
Entries tracked
22,310
Last sync
37 min
All sources syncing normally
  • Arena · Text8 hours ago
  • Arena · WebDev8 hours ago
  • Arena · Vision8 hours ago
  • Arena · Agent8 hours ago
  • GPQA Diamond37 minutes ago
  • SWE-bench37 minutes ago
  • Terminal-Bench37 minutes ago
  • ARC-AGI-237 minutes ago

Opus 5.5

63±1

60interval63

Anthropicswing #97–#97

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) ×14 of 1034 models
ModelOrgIntervalSwingiiiiiiiiiiiiiiiiiiiiiiAdd to compare
3Claude Opus 5.5 (High)anthropicOct 2026$4 / $2084.3 94.6Ranked 84.3 = (10 × 94.6 + 3 × 50) ÷ 13. 94.6 is the mean percentile over the 10 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.81–862410/22#2–1199100959976—10084100—9598——————————
6Claude Opus 5 (Max)anthropicSep 2026$5 / $2583.2 91.5Ranked 83.2 = (12 × 91.5 + 3 × 50) ÷ 15. 91.5 is the mean percentile over the 12 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.79–862012/22#5–11979692977989879492—8096—99————————
97Opus 5.5Anthropic——62.5 100.0Ranked 62.5 = (1 × 100.0 + 3 × 50) ÷ 4. 100.0 is the mean percentile over the 1 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.60–63—1/22low——————————————————100————
218Opus 5Anthropic——57.1 78.3Ranked 57.1 = (1 × 78.3 + 3 × 50) ÷ 4. 78.3 is the mean percentile over the 1 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50.54–58—1/22low——————————————————78————

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.