Benchmark Almanac

TextWorld Cooking (GATA)

Not in model cards

Agents navigate text-based rooms, gather ingredients, and prepare recipes. The port sums points earned during play and includes separate training and test games at increasing difficulties.

The highest public hub mean reward was 2.167 for Qwen3-4B-Thinking-2507 on 20 examples on December 30th, 2025. The hub also lists Qwen3-0.6B.

Made by
GATA authors
Released
February 2020
Kind
Video games
Level
Everyday
Scored
Settled by events
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Actions
Interaction
Agentic
Environment
TextWorld
Items from
Generated
Refresh
One fixed set
Run by
Anyone
In views
Games, Agents
Last model added
August 2025
Scores refreshed
November 20th, 2026
2
Models scored on Prime Intellect’s leaderboard

Qwen3-4B-Thinking-2507 leads with 2.17

Best score per model from Prime Intellect’s leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.

  1. 1 Qwen3-4B-Thinking-2507 20 examples 2.17
  2. 2 Qwen3-0.6B 20 examples 0.15

Source: Prime Intellect’s leaderboard

#ModelScoreSettingSubmitted byReleasedRun onLinkSource
1 Qwen3-4B-Thinking-2507 2.17 20 examples, verifiers Bryon Kucharski Aug 2025 Dec 2025 app.primeintellect.ai Official leaderboard
2 Qwen3-0.6B 0.15 20 examples, verifiers Bryon Kucharski Apr 2025 Dec 2025 app.primeintellect.ai Official leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On Prime Intellect’s leaderboard
0.00 0.50 1.00 1.50 2.00 2.50 2025 0.00 0.50 1.00 1.50 2.00 2.50 2025

Source: Prime Intellect’s leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Games and long tasks

All 261 in Games and long tasks
  • ARC-AGI-3 In use Interactive game environments where agents must explore, infer goals and rules, and act efficiently without instructions. GPT-6.2 Astra 100%
  • Orak Fading LLM agents play 12 popular video games across most genres through an MCP interface. Each game scores in-game progress or outcomes, and the board ranks models by their average rank across the games. Gemini 2.5 Pro 3.90
  • MineDojo Fading Agents complete open-ended tasks in Minecraft, such as mining blocks and fighting mobs, from a large simulation suite. Programmatic checks score many tasks. Seed2.0 Pro 49%
  • TextQuests Only in system cards Agents play 25 classic interactive fiction games. The score is harmful actions per 100 steps, where lower is better. The board also reports game progress. Llama 4 Scout 7.00
  • GameWorld Only in system cards Multimodal game agents play 34 browser games across 170 tasks. Outcomes are checked from the game state. GPT-6.1 Terra 76.8%
  • Swarm Bench Only in system cards Models orchestrate agent swarms on complex tasks that benefit from coordinated decomposition and parallel execution. Kimi K3 76.3%

Data audit

7 of 8 checks pass, 1 warning. Look first at the Newest score check. The newest came 15 months ago, in August 2025, for Qwen3-4B-Thinking-2507. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 1 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (2 entries).
  • Note Models scored Only 2 models we track.
  • Warning Newest score The newest came 15 months ago, in August 2025, for Qwen3-4B-Thinking-2507.
  • Note Frontier models None of its models are on the capabilities index.
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on Prime Intellect: 2 rows for models we track at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check