# CivBench

9 Hacker News commenters recommended CivBench and 1 criticized it, November 2025 to November 2026. It was recommended in 1 of 13 months.

**Verdict:** 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.

## Why people recommend it

- Enthusiastic praise for the idea (4 comments): "This is an amazing eval metric that no one thought about!" ([source](https://news.ycombinator.com/item?id=47156631)) "This is a sick idea I must say" ([source](https://news.ycombinator.com/item?id=47152775)) "This is undeniably intriguing." ([source](https://news.ycombinator.com/item?id=47155307))
- Live view of model behavior (2 comments): "If you want to see how these models actually behave under pressure (not just how they test), come watch live." ([source](https://news.ycombinator.com/item?id=46905503)) "Big fan of how you add visualization and interactivity to the typical model benchmarking process." ([source](https://news.ycombinator.com/item?id=47152798))
- Useful signal for frontier models (2 comments): "Continuous benchmarks like this are the only way to get signal on frontier models" ([source](https://news.ycombinator.com/item?id=47152922)) "Necessary for developers, users, and industries that want to use agents" ([source](https://news.ycombinator.com/item?id=47157710))

## Alternatives hackers recommend

- [Artificial Analysis](https://hackerapproved.com/p/artificial-analysis.md): 62 recommend
- [LMArena](https://hackerapproved.com/p/lmarena.md): 39 recommend
- [ARC-AGI](https://hackerapproved.com/p/arc-agi-3.md): 22 recommend
- [OCR Arena](https://hackerapproved.com/p/ocr-arena.md): 11 recommend
- [Bullshit Benchmark](https://hackerapproved.com/p/bullshit-benchmark.md): 9 recommend

## Cite as

Hacker Approved, "CivBench", https://hackerapproved.com/p/civbench/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).