GTA-Workflow - Creativity: leaderboard

Root success on the GTA-Workflow tasks that require creativity tools, part of GTA-Workflow, the open-ended tier of GTA-2 (2026): 132 long-horizon productivity workflows from real user queries with deployed tools and multimodal inputs, run end to end in a ReAct agent framework and judged by GPT-5.2 against recursive checkpoint rubrics. Percent; higher is better.

Metric: Root success rate (%) on the tasks that require creativity tools on GTA-Workflow, the open-ended long-horizon workflow tier of GTA-2 (132 real-user tasks with deployed tools and multimodal inputs), run end to end in the default Lagent ReAct framework; deliverables judged by GPT-5.2 against recursive checkpoint rubrics; higher is better. Source: arxiv.org. Saturation forecast: Around 2028. 13 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 2.5 Pro12.5#280
2GPT-58.33#185
3DeepSeek V3.28.33#425
4Claude Sonnet 4.54.17#267
5Grok 44.17#321
6Llama 3.2 3B Instruct4.17#7311
7Kimi K24.17#448
8Qwen 3 235B A22B4.17#633
9Llama 4 Scout4.17#1825
10Llama 3.1 8B Instruct0#4655
11Llama 3.1 70B Instruct0#1579
12Qwen 3 8B0#1890
13Qwen 3 30B A3B0#1165

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=gta-workflow-creativity · How It Works · Data refreshed daily, snapshot 2026-11-22.