---
title: "Head-to-head: games, simulators and real-time control"
type: community
source_tier: community
tags: [head-to-head, games, real-time, community]
created: 2026-09-25
updated: 2026-09-25
confidence: medium
sources:
  - raw/x/aimlapi-2100372930282573876.md
  - raw/x/aimlapi-2100372930282573876-video.md
  - raw/community/dev-to-maximsaplin-typesafe-jev-played-chess-and-landed-next-to-reasoning-models-28ga.md
  - raw/x-repos/trungdq88__jev-tetris.md
  - raw/x-repos/virajbhartiya__laya-vs-jev.md
  - raw/x/sl1ma4-2102008698767904981.md
  - raw/x/sl1ma4-2102008698767904981-video.md
  - raw/x/KashyapVisharad-2102350346031149183.md
  - raw/x-repos/shitianfang__jev-use__bench-results.md
  - raw/community/zenn-dev-nwn-articles-824026c76116e0.md
  - raw/x/staskulesh-2102062632517697652.md
  - raw/x/staskulesh-2102062632517697652-image.md
  - raw/x-repos/sliday__jev-chess-algo.md
  - raw/x-repos/ably-labs__jev-pong.md
  - raw/x-repos/PromptEngineer48__laya-vs-jev-arena.md
  - raw/x-repos/Contrastive-LM__CLM.md
  - raw/x-repos/Contrastive-LM__CLM__examples-t-rex-results-jev-realtime-json.md
  - raw/x-repos/Contrastive-LM__CLM__examples-t-rex-results-clm-realtime-json.md
  - raw/x-repos/sc2musa__Jev_Star.md
  - raw/x-repos/sc2musa__Jev_Star__paper-paper.md
jev_version: "jev-1.13.0"
summary: "Builder A/B runs of Jev in games and real-time control (chess, Pong, Tetris, Mario, Snake, T-Rex, StarCraft II) vs LLMs, local replicas, engines and people. Split from head-to-head."
---

# Head-to-head: games, simulators and real-time control

> **TL;DR** In games Jev's edge is decision speed and cost, not play strength: it beat slower chat models where a clock or real-time loop punishes latency (Tetris, Pong, Mario) but lost Tetris with no clock, lost to local replicas where raw decisions per second win (Snake, Clash Royale), never beat a chess engine and lost a blitz game to GPT-6 Astra, and did no better than random at StarCraft II until a planner constrained its actions. Code that builds the legal-move menu does part of the work. Split from [[ideas/head-to-head]] on 2026-09-25; rows moved unchanged.

Numbers as each builder published them, mostly one run or a handful of episodes, in 2026-09, when `jev-latest` pointed at `jev-1.13.0` ([[reference/models-and-pricing]]); rows that name no version are assumed on it (inferred). **LOST** = Jev lost on the stated goal. Pattern: [[ideas/patterns-data]] P24 games. The builds themselves: [[ideas/builds-games-and-devices]]; robot and embodied suites (Meta-World, LIBERO, ALFWorld) and the LLM Chess numbers: [[ideas/head-to-head-benchmarks]].

## Chess

| Task (builder) | Compared | Numbers as published | Won | Caveat |
|---|---|---|---|---|
| Chess, LLM Chess leaderboard ([Maxim Saplin](https://dev.to/maximsaplin/typesafe-jev-played-chess-and-landed-next-to-reasoning-models-28ga)) | vs the board's LLMs | Elo in the band of mid-pack reasoning models at a small fraction of their cost and time per game; numbers on [[ideas/head-to-head-benchmarks]] | Cost, latency; accuracy tie | Wide Elo interval; no Jev row on the live leaderboard yet |
| Blitz chess 5+0, one API call per move ([@aimlapi](https://x.com/aimlapi/status/2100372930282573876)) | vs Fable 5.1, GPT-6 Astra | Fable was +16 in material at move 29 (a second queen), then lost it back to Jev's king; with king and pawn each, Fable flagged at move 51 (Fable 3.3-15.0 s per move, median 5.4 s; Jev median 2.1 s). Astra mated Jev on its 18th move (Qe1#) with 2:27.7 left; Jev 1.0-1.7 s per move in that game | Clock vs Fable; **LOST** to Astra | One game each (video transcribed 2026-09-25). Jev's 1-2 s per move is above TypeSafe's 70–500 ms ([[concepts/system-one]]), so harness or route overhead is likely included (inferred) |
| Chess vs Komodo Dragon ([Maxim Saplin](https://dev.to/maximsaplin/typesafe-jev-played-chess-and-landed-next-to-reasoning-models-28ga)) | vs chess engine | Drew half its games at the low levels and never won; our tally of the unmerged harness branch found no engine wins at any level (`unverified`); numbers on [[ideas/head-to-head-benchmarks]] | **LOST** | Same run as the leaderboard row above. [[ideas/failure-reports]] |
| Crowd vs Jev, jevchess.com ([@staskulesh](https://x.com/staskulesh/status/2102062632517697652), [algo repo](https://github.com/sliday/jev-chess-algo)) | Jev vs anonymous human players | Share card of 2026-09-21 (image transcribed): 19-6 over 25 games (16 wins, 6 draws, 3 losses); compute shown as "18.2C" (last glyph unclear, a C or a cent sign) | Jev | Casual anonymous pool; every legal move is a Choice option plus a code-side hanging-piece check, so code does part of the work |

## Arcade and real-time games

| Task (builder) | Compared | Numbers as published | Won | Caveat |
|---|---|---|---|---|
| Three-option paddle decision, 40 states × 2 ([jev-use](https://github.com/shitianfang/jev-use), shitianfang) | vs Haiku 4.5 and Gemini 3 Flash, free-form and schema-constrained | p50 225 ms vs 691 (Haiku strict) / 1,027 (Gemini strict); $0.018 vs $0.30 / $0.09 per 1,000; quality 24-30 of 40 for every arm | Latency (3.0-3.1× vs constrained), cost; quality tie | The author withdrew his own "86 vs 6 decisions" Pong headline as an unconfigured baseline. Jev never chose `stay` in 80 calls: right on every move state, 0 of 13 hold states |
| Pong, 30 game states, Jev + 13 chat-model settings ([jev-pong](https://github.com/ably-labs/jev-pong), Ably Labs) | vs chat models via Vercel AI Gateway | 30-state run 2026-09-19: Jev 28/29 at 222 ms median (one Gateway 503 not counted); Ministral 3B 26/30 at 1.8× the latency; the other 12 configurations (11 models; GPT-6 Astra at two effort settings) 28-30/30 at 2.7-20.4×. Live lanes 2026-09-17: 4.4 vs 0.28-0.40 decisions/s, Jev 227 ms average | Latency; **LOST** a point | Author: a latency demo, not an intelligence demo |
| Super Mario harness, same machine ([nwn, Zenn](https://zenn.dev/nwn/articles/824026c76116e0), Japanese) | vs Llama 3.1 8B, Gemma 4 26B A4B, Qwen3 235B, Gemini 2.5 Flash-Lite (first-token logit read) | Distance 1,226 / 1,138 / 1,127 / 686 / 296 at 276 / 356 / 572 / 593 / 719 ms mean | All; narrowly vs Llama and Gemma | Only logprob-capable older, non-reasoning LLMs could be compared; his Jev latency was ~3× the public demo's. His logit read on Gemma3 270M ran 77× faster than generating JSON |
| Real-time Tetris, seed 42 ([trungdq88](https://github.com/trungdq88/jev-tetris)) | vs Claude Haiku 4.5 | Won all 3 modes; ~220 vs ~750 ms per move; ~20x cheaper per move | All | One run per mode |
| Same, Gemini 3.8 Flash | | Real time: Jev won (Gemini missed 8 deadlines). No clock: Gemini 0.32 lines per piece vs 0.25 at ~17x the cost per move | **LOST** with no clock | One seed |
| Tetris ([trungdq88](https://github.com/trungdq88/jev-tetris)) | vs Laya, 4-core CPU | Jev won at 0:14: 7 lines vs 0; 232 vs 614 ms per move | All | Laya near-flat; prefers first-listed options |
| Snake, 30 s ([@sl1ma4](https://x.com/sl1ma4/status/2102008698767904981)) | vs Laya, local | Laya 86.5 vs Jev 3.2 decisions/s (2,588 vs 95 decisions); score Laya 75 vs Jev 3 at 30 s (the post's 46 vs 1 is the 15 s mark); Jev P50 305.7 ms per step | **LOST** | Speed-bound game; Laya's window 512-1024 tokens |
| Snake race and fight arena ([laya-vs-jev-arena](https://github.com/PromptEngineer48/laya-vs-jev-arena), PromptEngineer48; not virajbhartiya's repo) | vs Laya, local | Video: Laya won the snake race 90-50 and the first fight; ~133 ms p50 local vs Jev ~962 ms from India. 8 fixed steering positions: Jev 8/8, Laya 7/8 | **LOST** speed; judgment Jev | Author: "Laya's edge here is speed, not judgment." |
| Chrome T-Rex ([CLM](https://github.com/Contrastive-LM/CLM), Contrastive-LM) | Jev vs a frozen embedder with a contrastive head, both under a physics-planner shield | Both survived; Jev agreed with the planner far more often, CLM was much faster. Numbers on [[ideas/eval-boards]] | Judgment Jev; **LOST** latency | CLM's survival is mostly the shield; its verifier claims against Jev are `unverified`. Replica row: [[ideas/open-replicas]] |

## Strategy games

| Task (builder) | Compared | Numbers as published | Won | Caveat |
|---|---|---|---|---|
| StarCraft II, realtime, Lv7 AI, 10 seeds per arm ([JEV-Star](https://github.com/sc2musa/Jev_Star), sc2musa; not the StarCraft 1998 row on [[ideas/builds-games-and-devices]]) | Jev vs uniform random, with and without a GPT-6 Astra planner (run through the Codex CLI). Macro: Protoss, 73 actions, realtime games (so decision latency is game time, inferred). Micro: SMAC-Hard with fixed stepping, one planner plan per map, Jev acting per unit | Wins / losses / time limits: Jev alone **0 / 10 / 0**, as random; planner-constrained random 0 / 10 / 0; planner-constrained Jev **9 / 1 / 0**; planner advisory 3 / 3 / 4. Micro, 35 maps × 3: Jev alone 3 wins, 2 draws, 100 losses; with planner 6-7 wins. Median 0.375-0.421 s over 19,605 responses | **LOST** alone; planner + Jev won | Author: version and timing differences block a causal reading. No top-level licence (third-party notices only) |
| Clash Royale, 1 match ([@KashyapVisharad](https://x.com/KashyapVisharad/status/2102350346031149183)) | vs Laya on a Mac | Laya won | **LOST** | n = 1 |

## How to read these

- **Speed decides real-time games.** Where the game waits for no one, the faster decider wins: Jev over chat models (Tetris, Pong, Mario), local replicas over Jev (Snake, Clash Royale). Remove the clock and a slower model can out-play it (Tetris vs Gemini). Jev Pong's author calls it a latency demo, not an intelligence demo.
- **Judgment and speed separate.** In fixed steering positions and next to a physics shield Jev judged as well or better than the local model that beat it on speed (laya-vs-jev-arena, CLM T-Rex).
- **Code does part of the work.** Legal-move menus, hanging-piece checks, shields and planners carry much of the result: trust notes say planner-assisted game scores measure the planner plus the model ([laya-vs-jev](https://github.com/virajbhartiya/laya-vs-jev)); JEV-Star only won with a planner constraining its actions.
- **Chess: cheap, not strong.** Jev never beat an engine and lost a blitz game to GPT-6 Astra; its cheap, fast games still placed it near mid-pack reasoning models on Elo.
- **Check the answer distribution**, not only accuracy: the jev-use paddle question never chose `stay` ([[ideas/failure-reports-confidence]]).

## Related

- [[ideas/head-to-head]]: app-level comparisons and cascades; [[ideas/head-to-head-benchmarks]]: public suites; [[ideas/head-to-head-agents]]: agent A/Bs; [[ideas/cost-ledger]]: cost per decision
- [[ideas/builds-games-and-devices]]: the game and device builds; [[ideas/failure-reports]]: where games broke; [[ideas/open-replicas]]: Laya and other replicas
- [[concepts/jaggedness-jev-1-13]]: documented failure modes to check before a game build

## Sources

Links inline; raw captures listed in the frontmatter (private repo). The llm_chess engine tally comes from our own 2026-09-24 vetting of the harness branch, not a capture ([[ideas/head-to-head-benchmarks]]).