# Jev vs. GPT-5.6 and Claude Haiku at Pong

> Jev returns a decision in 227 ms. The chat models take 2.5 to 3.5 seconds. Pong where the ball moves one step per model decision. Slow model, slow ball.

Page: https://nowfound.app/launch/jev-vs-gpt-5-6-and-claude-haiku-at-pong

- Launched: 2026-09-18
- Launch-day votes: 10, 4 comments; #1,000 of 8,095 launches that month (top 12%)
- Website: [jev-pong.ably.dev](https://jev-pong.ably.dev/), online when checked 2026-09-18
- Category: [AI](https://nowfound.app/c/ai.md)

## In plain words

Jev vs. GPT-5.6 and Claude Haiku at Pong is a comparison tool that plays the classic Atari game simultaneously with different AI models. Each model controls a paddle in its own lane, and the ball moves one step per model response, making response speed directly visible. Jev, a typed-decision model, completes decisions in 227 milliseconds, while chat-based models take 2.5 to 3.5 seconds, resulting in noticeably slower gameplay. The tool is for developers and researchers examining real-world performance differences between model architectures.

## Does a similar job

- [Jev](https://nowfound.app/launch/jev): Fast, structured AI decisions for software automation (2026-09-21, 544 votes, console.typesafe.ai)
- [Jevman – AI decision models play Pac-Man](https://nowfound.app/launch/jevman-ai-decision-models-play-pac-man): Six AI decision models played Pac-Man in real time against the classic arcade ghosts. See the leaderboard, watch their games, or play against them. (2026-10-08, 81 votes, opper.ai)
- [I taught AI to commentate Pong in real time](https://nowfound.app/launch/i-taught-ai-to-commentate-pong-in-real-time): LLM-generated real-time commentary for Pong. Contribute to pncnmnp/xpong development by creating an account on GitHub. (2025-05-02, 207 votes, github.com)
- [Real-time AI Voice Chat at ~500ms Latency](https://nowfound.app/launch/real-time-ai-voice-chat-at-500ms-latency): Have a natural, spoken conversation with AI! Contribute to KoljaB/RealtimeVoiceChat development by creating an account on GitHub. (2025-05-05, 524 votes, github.com)
- [GPT‑5.4 mini and nano](https://nowfound.app/launch/gpt-5-4-mini-and-nano): Fast and efficient models optimized for coding and subagents (2026-03-18, 263 votes, openai.com)
- [Jevstiller – Distill Jev into a local model, with a disagreement bound](https://nowfound.app/launch/jevstiller-distill-jev-into-a-local-model-with-a-disagreemen): September 2026. Every number here is from the benchmarks, and bash experiments/bench.sh --no-record reruns them without an API key. (2026-09-29, 67 votes, jevstiller.pages.dev)

All alternatives: https://nowfound.app/alternatives/jev-vs-gpt-5-6-and-claude-haiku-at-pong.md
