GTA-Workflow - Leaf Success Rate: leaderboard
Leaf checkpoint success on 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: the share of leaf checkpoints scoring above 7 of 10. Percent; higher is better.
Metric: Leaf success rate (%): share of leaf checkpoints scoring above 7 of 10 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 February 2027. 13 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 28.46 | #276 |
| 2 | Llama 4 Scout | 27.51 | #1818 |
| 3 | GPT-5 | 26.3 | #178 |
| 4 | Claude Sonnet 4.5 | 26.21 | #261 |
| 5 | Qwen 3 235B A22B | 26.04 | #628 |
| 6 | DeepSeek V3.2 | 25.61 | #419 |
| 7 | Kimi K2 | 25.35 | #443 |
| 8 | Grok 4 | 25.17 | #319 |
| 9 | Llama 3.1 70B Instruct | 3.37 | #1571 |
| 10 | Llama 3.1 8B Instruct | 1.47 | #4600 |
| 11 | Qwen 3 30B A3B | 1.3 | #1156 |
| 12 | Llama 3.2 3B Instruct | 0.78 | #7241 |
| 13 | Qwen 3 8B | 0.69 | #1873 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=gta-workflow-leaf-success-rate · How It Works · Data refreshed daily, snapshot 2026-11-21.