MarginLab Claude Code tracker
Hacker ApprovedBenchmark tracker in Developer tools
Recommended as a benchmark repeated over time to detect Claude Code degradation; critics say small daily samples leave wide confidence intervals.
Recommended as a benchmark repeated over time to detect Claude Code degradation; critics say small daily samples leave wide confidence intervals.
14 people gave an opinion
- recommend it
- 10
- criticize it
- 4
- approval share
- 71%
Recommended in 8 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: not recommended
- September 2026: recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 10 people recommend itNeeds 10 or more, met.
- 2.5 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 8 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Repeated benchmark tracks nerfing
“To detect nerfing of a model, projects like https://marginlab.ai/trackers/claude-code/ are much much better”
Comment from 14 May 2026 on Hacker News “The site you linked is a much better example of a real benchmark being repeated over time.”
Comment from 21 Sep 2026 in “Fable 5 – Median thinking declined in August” “sites with ongoing measurements checking if a model has been nerfed”
Comment from 1 Oct 2026 in “Gemini 4 Argon (High): Intelligence, Performance and Price Analysis”
What people said
All 15 comments that mention it, newest first. Each links to the original comment.
“sites with ongoing measurements checking if a model has been nerfed”
“Need one of these for openai”
“This page has been in 'New model — collecting baseline data. Degradation detection paused.' state for months now.”
“The site you linked is a much better example of a real benchmark being repeated over time.”
“Has been pretty accurate when pre-release quality or bugs pop up”
“its open source and available to all”
“To detect nerfing of a model, projects like https://marginlab.ai/trackers/claude-code/ are much much better”
“That performance monitor is super easy to game if you cache responses to all the SWE bench questions.”
“the inter-run variability is too high to diagnose anything short of catastrophic model degradation”
“why should we trust this random bench?”
“the benchmark results don't cover the interesting "mid February" inflection point”
“Kudos for the methodology. The only question I can come up with is that if the benchmarks are representative of daily use.”
“since they only sample 50 tasks per day, the confidence intervals are very wide”
“Nice work, It would be really cool to be able to subscribe”
“Saw this the other day and loved it.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.