GeoAgentBench (Base Agent) - Tool Exact Match: leaderboard
Metric: Tools-Exact-Match (%): share of the ground-truth tool sequence matched exactly from the first step, on 53 spatial analysis tasks over 117 atomic GIS tools in an executable sandbox (30 steps per task), agents under the base agent paradigm (zero-shot tool scheduling without execution feedback); higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.6 | 53.01 |
| 2 | Gemini 2.5 Flash | 52.87 |
| 3 | DeepSeek V3 | 50.8 |
| 4 | GPT-4o | 45.8 |
| 5 | GPT-4o Mini | 29.74 |
| 6 | Llama 3.1 8B Instruct | 29.58 |
| 7 | Qwen 2.5 7B Instruct | 13.56 |
Interactive version: theaggregate.ai/benchmark?slug=geoagentbench-base-agent-tool-exact-match · How It Works · Data refreshed daily, snapshot 2026-10-07.