FrontierCode
Hacker ApprovedThe most recommended of 4 coding benchmarks
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.
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.
18 people gave an opinion
- recommend it
- 14
- criticize it
- 4
- approval share
- 78%
Recommended in 5 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: not recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: recommended
- September 2026: recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 14 people recommend itNeeds 10 or more, met.
- 3.5 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 5 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
Well reasoned and carefully built
“they are very well defined and solid coverage of everything one should want out of code”
Comment from 8 Jun 2026 in “FrontierCode” “Well reasoned, tons of work put into eval, thanks for building it.”
Comment from 8 Jun 2026 in “FrontierCode” “more thoughtful than any benchmark that I've seen until now”
Comment from 9 Jun 2026 in “FrontierCode” Top pick among coding benchmarks
“DeepSWE and FrontierCode are more realistic if you read up on what they actually measure.”
Comment from 21 Jul 2026 in “Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber” “Cognition's Frontier Code is probably the best large public benchmark at this.”
Comment from 24 Jul 2026 in “Why Software Factories Fail” “Only look at DeepSWE and FrontierCode right now for coding imo.”
Comment from 9 Jul 2026 in “GPT-5.6” Grades whether code would get merged
“The later is more interesting for me personally, due to the design of the benchmark heavily grading "mergability"”
Comment from 8 Jul 2026 in “Separating signal from noise in coding evaluations” “First benchmark to measure: "would this code get actually merged?"”
Comment from 8 Jun 2026 in “FrontierCode” Matches real-world coding experience
“the only benchmark that aligns with my actual LLM experiences”
Comment from 3 Sep 2026 in “GPT-6 Astra” “FrontierCode matches the vibes a lot better”
Comment from 2 Jul 2026 in “CursorBench 3.1”
What people warn about
Each mark is one comment
Maker's own benchmark, scores questioned
“AA seems to have accepted Cognition's benchmark scores without questioning”
Comment from 28 Oct 2026 in “Artificial Analysis Intelligence Index v5” “on their own benchmark that they made”
Comment from 10 Sep 2026 in “Cognition launches new SWE-2 model, Rivaling Fable 5.1 and GPT-Astra” Results contradict other benchmarks
“Any benchmark that shows gpt-6 sol as better than gpt-5.6 sol is incredibly suspect.”
Comment from 28 Oct 2026 in “FrontierCode 2.0” “this has dramatically different results, I don't trust it at all!”
Comment from 27 Oct 2026 in “FrontierCode 2.0”
Other coding benchmarks people recommend
The three most recommended other coding benchmarks, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| FrontierCodeThis page | 14 | 4 | 78% | 5 | — | Approved |
| Terminal-Bench | 12 | 11 | 52% | 10 | — | — |
| SWE-Bench Pro | 5 | 6 | 45% | 4 | — | — |
| SWE-bench | 5 | 17 | 23% | 2 | — | — |
What people said
All 23 comments that mention it, newest first. Each links to the original comment.
“Any benchmark that shows gpt-6 sol as better than gpt-5.6 sol is incredibly suspect.”
“AA seems to have accepted Cognition's benchmark scores without questioning”
“FrontierCode 1.1 is my favorite benchmark”
“this has dramatically different results, I don't trust it at all!”
“on their own benchmark that they made”
“the only benchmark that aligns with my actual LLM experiences”
“it was calibrated by 20+ open source maintainers”
“Cognition’s Frontier Code comes to mind”
“Cognition's Frontier Code is probably the best large public benchmark at this.”
“DeepSWE and FrontierCode are more realistic if you read up on what they actually measure.”
“"Good" benchmarks to gauge development skills at the moment seem to be”
“Only look at DeepSWE and FrontierCode right now for coding imo.”
“1.1 seems a lot better than the original release”
“The later is more interesting for me personally, due to the design of the benchmark heavily grading "mergability"”
“FrontierCode matches the vibes a lot better”
“whats the logic in claiming its a borked metric when everything listed is an anthropic model.”
“which is substantial progress in benchmarking”
“I'm liking the effort to make new, no-longer-saturated benchmarks.”
“You know that it's a honest benchmark when their own model (SWE-1.6) scores terrible on it.”
“more thoughtful than any benchmark that I've seen until now”
“they are very well defined and solid coverage of everything one should want out of code”
“Well reasoned, tons of work put into eval, thanks for building it.”
“First benchmark to measure: "would this code get actually merged?"”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.