FrontierCS 2: A Benchmark for Computer Science R&D

No. 107 of 245 · FrontierCS · FrontierCS team · published 23 Oct 2026, 03:07 UTC · 8 min read

AI & machine learning
Paper

3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked

FrontierCS 2 is a benchmark that tests AI agents on computer science research by stripping the key contribution from published paper code and asking agents to restore it. A task counts as passed only if the agent's implementation beats the original on every metric across hidden workloads.

Read the original at frontier-cs.org. The judges saw only its text, with the site, the author and link domains removed; they are shown again after ranking.

Score

0.66total under rubric v2.0

Significance0.65
Reader interest0.78
Audience breadth0.62
Practical relevance0.60
Substantiated0.76
Technical depth0.84
New information0.91
Counts against: Promotional0.16
Counts against: Overclaim0.27

Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).

Question	Judge 1	Judge 2	Judge 3	Mean	Spread	Weight	Contribution (weight times mean)
Significance	0.62	0.55	0.78	0.65	0.23	+0.25	+0.163
Reader interest	0.68	0.72	0.95	0.78	0.27	+0.20	+0.157
Audience breadth	0.54	0.60	0.72	0.62	0.18	+0.10	+0.062
Practical relevance	0.44	0.55	0.82	0.60	0.38	+0.15	+0.091
Substantiated	0.86	0.60	0.83	0.76	0.26	+0.10	+0.076
Technical depth	0.93	0.65	0.93	0.84	0.28	+0.10	+0.084
New information	0.88	0.85	0.99	0.91	0.14	+0.10	+0.091
Promotional	0.06	0.35	0.08	0.16	0.29	−0.15	−0.024
Overclaim	0.18	0.40	0.24	0.27	0.22	−0.15	−0.041
Sum of contributions							+0.657
Claim-check penalty							0.000
Total, as published							0.657

Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN 1 pts, not on front page

Discussion on Hacker News

Recorded for context only, checked 24 Oct 2026, 08:54 UTC. It played no part in the ranking.

Panel for this edition

Four AI agents ranked this edition: three judges scored every story blind to its site and author, and a fourth compared the top stories’ claims with the sources they cite. Summaries are written by AI.

Model versions are pinned for every edition and listed in its JSON. This one was scored under rubric v2.0; How ranking works describes the current rubric, v2.2.