Jon Saad-FalconandClaude Opus 4.6 fc369b9ab0 fix: use Claude Opus 4.6 as sole baseline for leaderboard savings ...

Dollar savings were previously summed across all three cloud providers
(GPT-5.3 + Claude Opus 4.6 + Gemini 3.1 Pro), inflating the reported
number by ~3x. Now uses only Claude Opus 4.6 pricing as the baseline,
with an asterisk footnote on the leaderboard explaining this.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-03-26 18:59:40 -07:00

..

architecture

feat: Algolia DocSearch + learning subsystem reorganization (#43)

2026-03-12 21:34:31 -07:00

assets

init commit

2026-03-12 17:29:39 +00:00

deployment

init commit

2026-03-12 17:29:39 +00:00

development

feat: add take-bot workflow and update contribution docs

2026-03-25 03:35:53 +00:00

getting-started

fix: address installation failures and SDK bugs (#100)

2026-03-24 16:29:26 -07:00

includes

init commit

2026-03-12 17:29:39 +00:00

javascripts

fix: correct O(N²) energy/FLOPs savings calculation (#95) (#97)

2026-03-20 18:52:18 -07:00

overrides

feat: Algolia DocSearch + learning subsystem reorganization (#43)

2026-03-12 21:34:31 -07:00

stylesheets

adding pagination and limiting to 50 per sign up on leaderboard

2026-03-16 15:58:39 -07:00

testing

feat: add Gmail/Twitter channel adapters, curated templates, channel contract tests, and QA runbook

2026-03-16 21:05:37 -07:00

tutorials

init commit

2026-03-12 17:29:39 +00:00

user-guide

feat: add SSE streaming support for managed agent messages

2026-03-24 14:56:58 +01:00

downloads.md

docs: update download links to v1.0.0

2026-03-12 10:54:38 -07:00

gen_ref_pages.py

init commit

2026-03-12 17:29:39 +00:00

index.md

docs: refresh landing page — clearer primitives, research section, citation (#59)

2026-03-14 16:02:17 -07:00

leaderboard.md

fix: use Claude Opus 4.6 as sole baseline for leaderboard savings

2026-03-26 18:59:40 -07:00