CivBench
Shares rank 5 of 10 AI benchmarks by recommenders
People recommend it as a live, interactive benchmark showing how AI models plan in multi-agent games. Caveat: one critic says current models are still weak at it.
People recommend it as a live, interactive benchmark showing how AI models plan in multi-agent games. Caveat: one critic says current models are still weak at it.
10 people gave an opinion
- recommend it
- 9
- criticize it
- 1
- approval share
- 90%
Recommended in 1 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: recommended
- March 2026: not recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 9 people recommend itNeeds 10 or more, not met.
- 9 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 1 of 13 monthsNeeds 4 or more, not 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
Enthusiastic praise for the idea
“This is an amazing eval metric that no one thought about!”
Comment from 25 Feb 2026 in “Show HN: CivBench a long-horizon AI benchmark for multi-agent games” “This is a sick idea I must say”
Comment from 25 Feb 2026 in “Show HN: CivBench a long-horizon AI benchmark for multi-agent games” “This is undeniably intriguing.”
Comment from 25 Feb 2026 in “Show HN: CivBench a long-horizon AI benchmark for multi-agent games” - Comment from 26 Feb 2026 in “Show HN: CivBench a long-horizon AI benchmark for multi-agent games”
Live view of model behavior
“If you want to see how these models actually behave under pressure (not just how they test), come watch live.”
Comment from 5 Feb 2026 in “Live agent face-off in CivBench: Claude Opus 4.6 vs. GPT-5.2” “Big fan of how you add visualization and interactivity to the typical model benchmarking process.”
Comment from 25 Feb 2026 in “Show HN: CivBench a long-horizon AI benchmark for multi-agent games” Useful signal for frontier models
“Continuous benchmarks like this are the only way to get signal on frontier models”
Comment from 25 Feb 2026 in “Show HN: CivBench a long-horizon AI benchmark for multi-agent games” “Necessary for developers, users, and industries that want to use agents”
Comment from 25 Feb 2026 in “Show HN: CivBench a long-horizon AI benchmark for multi-agent games”
Other AI benchmarks people recommend
The four most recommended other AI 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 |
|---|---|---|---|---|---|---|
| Artificial Analysis | 62 | 46 | 57% | 11 | — | — |
| LMArena | 39 | 40 | 49% | 11 | — | — |
| ARC-AGI | 22 | 24 | 48% | 8 | — | — |
| OCR Arena | 11 | 4 | 73% | 4 | — | Approved |
| CivBenchThis page | 9 | 1 | 90% | 1 | — | — |
What people said
All 11 comments that mention it, newest first. Each links to the original comment.
“So amazing, it's super cool!”
“This looks incredible, it'd be cool to let others participate with custom prompts”
“Necessary for developers, users, and industries that want to use agents”
“This is an amazing eval metric that no one thought about!”
“This is an amazing product! Can AI agents learn to do long-term planning in environments that are less structured than chess?”
“This is undeniably intriguing.”
“they're pretty bad at this point but I expect them to get much better overtime”
“Continuous benchmarks like this are the only way to get signal on frontier models”
“Big fan of how you add visualization and interactivity to the typical model benchmarking process.”
“This is a sick idea I must say”
“If you want to see how these models actually behave under pressure (not just how they test), come watch live.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.