Files
OpenJarvis/docs/leaderboard.md
T
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

2.1 KiB

hide
hide
navigation

Savings Leaderboard

See how the OpenJarvis community saves money, energy, and compute by running AI locally instead of using cloud providers.

!!! info "Win a Mac Mini!" Opt in to share your savings from the OpenJarvis browser app or desktop app for a chance to win a Mac Mini. Your data is fully anonymous — no email, no IP, no hardware info.

Community Members
Total Saved*
Total Requests
Total Tokens
# Name $ Saved* Energy (Wh) FLOPs Requests Tokens
Loading leaderboard...

*Dollar savings estimated vs. Claude Opus 4.6 API pricing ($5/1M input, $25/1M output tokens). Assumes local open-source models produce roughly the same number of tokens per request as cloud models.