The best coding benchmarks, according to hackers
4 coding benchmarks were recommended on Hacker News between November 2025 and November 2026. We rank them by how many separate people recommend each one, and 1 earns the Hacker Approved badge.
Top pick
The most recommended coding benchmark with the badge. Each figure is one person. RecommendsCriticizes One comment
Well reasoned and carefully built
Recommended as a public coding benchmark that grades whether code would get merged and was calibrated with open source maintainers. Critics question its scores and results.
All 4 coding benchmarks, ranked
Select a column heading to sort. Approval share is recommenders out of everyone who gave an opinion; the tick on each bar marks the 2 to 1 line the badge needs. Months counts the months, out of 13, in which someone recommended it.
| Rank | |||||||
|---|---|---|---|---|---|---|---|
| 1 | FrontierCode | 14 | 4 | 78% | 5 | — | Approved |
| 2 | Terminal-Bench | 12 | 11 | 52% | 10 | — | — |
| Tied 3 | SWE-Bench Pro | 5 | 6 | 45% | 4 | — | — |
| Tied 3 | SWE-bench | 5 | 17 | 23% | 2 | — | — |
How we rank
Rank is the number of separate people who recommend a product in a Hacker News comment over the past year. Someone who praises the same coding benchmark in five threads counts once.
The badge goes to coding benchmarks that at least 10 people recommend, with recommenders outnumbering critics at least 2 to 1, recommended in at least 4 of the 13 months.
Rankings are never for sale. We may earn a commission when you buy through our links. It never changes the order.