RoadmapBench - Completion Score: leaderboard
RoadmapBench (2026) tests coding agents on 115 long-horizon tasks built from real open-source version upgrades in 17 repositories and five languages: from the earlier release and a roadmap of subtasks, the agent must implement the next release, with each subtask checked by its own tests. This board is the completion score: the complexity-weighted share of subtasks whose tests pass, averaged over tasks and given in percent; higher is better.
Metric: Completion score (%): mean over tasks of the complexity-weighted share of roadmap subtasks whose own test suites pass, times 100, 115 long-horizon tasks implementing a real release upgrade from a roadmap of subtasks, one trial per model, 2-hour wall-clock budget, extended thinking on; each row names its agent scaffold (OpenHands, the primary scaffold, or Terminus 2, the ablation); higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 13 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Opus 4.7 | xHigh | 69.2 | #85 |
| 2 | Claude Opus 4.6 | Thinking | 62.7 | #113 |
| 3 | GPT-5.4 | High | 49.7 | #135 |
| 4 | DeepSeek V4 Pro | High | 48.6 | #196 |
| 5 | GLM-5.1 | 45.3 | #198 | |
| 6 | MiMo-V2.5-Pro | 44 | #284 | |
| 7 | Gemini 3.1 Pro (Preview) | High | 43.9 | #99 |
| 8 | Kimi K2.6 | 43.2 | #192 | |
| 9 | Qwen 3.6 Plus | 42.4 | #238 | |
| 10 | Qwen 3.5 397B A17B | 38.3 | #264 | |
| 11 | Kimi K2.5 | 37.8 | #266 | |
| 12 | MiniMax-M2.7 | 33.2 | #539 | |
| 13 | Seed 2.0 Pro | High | 17.7 | #222 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=roadmapbench-completion-score · How It Works · Data refreshed daily, snapshot 2026-11-21.