MapSatisfyBench - Explicit Completion: leaderboard
Metric: Explicit-factor completion rate (%): share of the query's stated requirements the final response satisfies; underspecified map-service requests rebuilt from real anonymized user behavior chains, answered by a ReAct agent with 22 deterministic replayed map tools and a simulated user; GPT-5.3 simulates the user and judges (majority of three judgments), temperature 1; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) (Thinking) | 91.75 |
| 2 | Claude Opus 4.6 | 91.48 |
| 3 | DeepSeek V4 Pro (Non-reasoning) | 90.88 |
| 4 | Qwen 3.6 Plus (Thinking) | 90.68 |
| 5 | DeepSeek V3.2 (Non-reasoning) | 90.19 |
| 6 | GPT-4.1 | 89.97 |
| 7 | Claude Sonnet 4.6 | 89.83 |
| 8 | Qwen 3.6 Plus (Non-reasoning) | 89.59 |
| 9 | Qwen 3 235B A22B (Non-reasoning) | 88.35 |
| 10 | Qwen 3 8B (Non-reasoning) | 69.97 |
| 11 | Qwen 3 30B A3B (Non-reasoning) | 60.83 |
Interactive version: theaggregate.ai/benchmark?slug=mapsatisfybench-explicit-completion · How It Works · Data refreshed daily, snapshot 2026-09-29.