cd /news/artificial-intelligence/claude-code-in-unity-we-benchmarked-… · home topics artificial-intelligence article
[ARTICLE · art-88209] src=ziva.sh ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

Claude Code in Unity: We Benchmarked It on a Game

In a benchmark of AI coding agents building a Flappy Bird game in Unity, Claude Opus 5 scored 10/10 and shipped a working game with a 306-line PlayMode test suite, while Claude Sonnet 5 scored 5/10 because it placed the ground at y = −250, making the game unplayable. DeepSeek v4 Flash, a free model, delivered a full game for $0.61, and DeepSeek v4 Pro matched the 9/10 score but cost $11.96 due to zero cache reads. The benchmark, run by Ziva in the Unity editor beta, used three prompts with a 20-minute cap per model.

read2 min views1 publishedAug 4, 2026
Claude Code in Unity: We Benchmarked It on a Game
Image: Ziva (auto-discovered)

Ziva runs docked in the Unity editor now, in beta, so we reran our Godot benchmark there: build a playable Flappy Bird as an agent, three prompts, 20-minute cap each. Claude ran on a Pro/Max subscription.

| Model | Tool calls | Wall time | Build cost | Rubric | Stars |

|---|---|---|---|---|---|
| DeepSeek v4 Flash (free) | 158 | 45.6 min (2 capped) | $0.61 | 9/10 | 3/5 |

| DeepSeek v4 Pro | 413 | 42.9 min (1 capped) | $11.96* | 9/10 | 3/5 | Claude Sonnet 5 (BYO) | 384 | 28.2 min | $7.34* | 5/10 | 2/5 | Claude Opus 5 (BYO) | 213 | 33.6 min | $14.73* | 10/10 | 4/5 |

  • List-price equivalents, not billed: Claude ran on a subscription and this account has a 100%-off promotion on Pro. Flash’s 61 cents is real spend. Sonnet 5 wrote the cleanest code and a game you cannot play. The scripts are correct; the scene is not. The camera sees y −5 to +5; Sonnet put the Ground at y = −250, so the bird dies before the first pipe arrives.

Opus 5 shipped a working game and, unprompted, a 306-line PlayMode suite — twelve tests, run sixteen times, ending at thirteen passing. One failure (“an in-flight keypress must not skip the overlay”) is why it added a restart delay.

DeepSeek v4 Flash, the free model, shipped a full game for 61 cents — built entirely in code — but capped on two turns. Same prompts cost $0.18 in Godot.

DeepSeek v4 Pro matched that 9/10 in 413 calls, but made zero cache reads to Flash’s 10.4 million — most of the twenty-fold cost gap.

Unity went from 12 tools to 21 this release, adding run_tests

, find_gameobjects

and manage_asset

. Two of four models used run_tests

unasked.

Caveats: n=1 per model, one task type, wall times not comparable across engines. One Unity-beta defect cost three runs — a changed-API edit raises a modal dialog that blocks the

editor, and -accept-apiupdate doesn’t stop it. The beta is in Ziva.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @ziva 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/claude-code-in-unity…] indexed:0 read:2min 2026-08-04 ·