Agents on Rails - Feature Ticket Score: leaderboard
Partial-credit hidden-test scores over 20 feature-size Rails tickets, using lemans/miniswen. Every task has equal weight after its runs are averaged; native run counts and explicit effort are retained. This is distinct from the legacy successful-run percentage.
Metric: Mean Task Score (%). Source: rubyonrails.org. Saturation forecast: Around November 2027. 13 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5.5 (xHigh) | 59.15 | #3 (Claude Opus 5.5) |
| 2 | GPT-6 Astra (xHigh) | 57.8 | #5 (GPT-6 Astra) |
| 3 | Gemini 4 Argon (High) | 53.1 | #7 (Gemini 4 Argon) |
| 4 | GPT-6.1 Sol (xHigh) | 52.9 | #8 (GPT-6.1 Sol) |
| 5 | GPT-6 Astra (Medium) | 52 | #5 (GPT-6 Astra) |
| 6 | Claude Opus 5.5 (Medium) | 48.25 | #3 (Claude Opus 5.5) |
| 7 | Grok 4.7 (High) | 38.45 | #27 (Grok 4.7) |
| 8 | GPT-6 Luna (Max) | 30.8 | #52 (GPT-6 Luna) |
| 9 | Kimi K3 (Max) | 28.7 | #30 (Kimi K3) |
| 10 | Muse Spark 1.3 (Max) | 27.3 | #25 (Muse Spark 1.3) |
| 11 | DeepSeek V4.1 Flash (Max) | 24.5 | #36 (DeepSeek V4.1 Flash) |
| 12 | GLM-5.3 Flash (Max) | 22.15 | #66 (GLM-5.3 Flash) |
No result here: #9 Claude Fable 5.1, #10 Claude Sonnet 5.5.
Interactive version: theaggregate.ai/benchmark?slug=agents-on-rails-feature-ticket-score · How It Works · Data refreshed daily, snapshot 2026-10-16.