SEELE02-pro tops GameCraft-Bench with a 43.8% overall score — 2.3 points ahead of the nearest competitor (Claude Code / Opus-4.7, 41.5%).
RESULTS
GameCraft-Bench evaluates AI agents on 140 real Godot game-development tasks. Agents are ranked by raw score; each score reflects the final effective attempt per task, evaluated by hidden Godot validation scripts and a multimodal judge.
LEADERBOARD
SEELE02-pro row uses the final effective validation results from the Seele report. External rows follow the GameCraft-Bench leaderboard reference.
| Rank | Model | Harness | Feedback | Cases | Score |
|---|---|---|---|---|---|
| 1 | SEELE02-pro | SeeleAgent | Baseline | 140 | 43.8% |
| 2 | Opus-4.7 high | Claude Code | Baseline | — | 41.5% |
| 3 | GPT-5.5 high | Codex | Baseline | — | 39.5% |
| 4 | Kimi-K2.6 | Kimi Code | Baseline | — | 30.7% |
| 5 | MiMo-V2.5-Pro | Claude Code | Baseline | — | 24.1% |
| 6 | GLM-5.1 | Code Buddy | Baseline | — | 18.3% |
| 7 | MiniMax-M2.7 | Code Buddy | Baseline | — | 11.0% |
| 8 | DeepSeek-V4-Pro | Codex | Baseline | — | 2.2% |
KEY FINDINGS
The headline takeaways from the leaderboard above — every figure traces back to the official GameCraft-Bench evaluation.
SEELE02-pro tops GameCraft-Bench with a 43.8% overall score — 2.3 points ahead of the nearest competitor (Claude Code / Opus-4.7, 41.5%).
All 140 cases were completed and scored in the final effective run — full coverage of the benchmark with no gaps.
The highest-scoring case hit 87.2%, demonstrating the model can handle complex Godot tasks with high fidelity.
Every score comes from the official verifier pipeline and hidden rubric — model self-reporting is never counted as evidence of success.
WHAT IS GAMECRAFT-BENCH?
GameCraft-Bench is an open-source benchmark of 140 real Godot game-development tasks across 15 game families — from platformers and strategy to roguelikes and visual novels. Each task asks an agent to turn a natural-language game specification into a complete, playable Godot project. Unlike pass/fail coding benchmarks, every case is graded on a percentage scale by the official verifier pipeline and a multimodal judge, so the overall score measures how completely an agent ships a working game — not just whether code compiles.
Each submission is exported as a complete, runnable Godot project. An automated verifier replays recorded demo traces, and a multimodal judge scores the result against a hidden rubric.
Overall score is the raw sum of per-case scores divided by total cases. Each case is scored by a hidden rubric; model self-reporting is never counted as evidence of success.
EXAMPLE TASKS
These examples are compressed from real GameCraft-Bench task descriptions, preserving the actual task substance while making them readable on the page.
Implement a persistent inventory system that saves item state to disk and restores it across sessions, using Godot’s ResourceSaver and ResourceLoader.
Build a heads-up display with a real-time minimap rendered via SubViewport, player health bar, and ammo counter using Control nodes and custom drawing.
Wire an AnimationTree with a BlendSpace2D for directional movement, transition guards for idle/run/jump states, and call-method tracks for footstep SFX.
Create a physics puzzle where the player drags and stacks RigidBody3D crates to reach a trigger zone, with collision filtering and stability thresholds.
Write a spatial shader with a noise-driven dissolve threshold, edge glow, and color ramp that triggers on enemy health change via uniform updates.
Use TileMapLayer with custom tile data to generate a bounded dungeon from a walker algorithm, placing walls, floors, and chests with collision metadata.
SOURCES
SeeleAgent builds 2D and 3D games — mobile and multiplayer — with export to Unity 6, Three.js, and WebGL, and distribution to Steam, App Store, and Google Play. Open the workspace and ship your first game, video, or scene tonight.