C2A Bench - Support Agent Knowledge: leaderboard
Observe.AI C2A Bench (observeai/c2a-bench) Support Agent Knowledge domain: builder models build a customer-support agent across 5 doc-quality conditions (complete, fragmented, incomplete, conflicting, noisy; 67 graded tickets each) with runtime agent fixed to openai/gpt-5.6-sol. Mean ticket pass rate (0-100%); higher is better.
Metric: Ticket Pass Rate (%). Source: huggingface.co. Saturation forecast: Not forecast. 7 models tracked. Updated 21 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Gemini 4 Carbon | High | 78.51 | #7 |
| 2 | DeepSeek V4.1 Flash (1017) | High | 76.72 | #47 |
| 3 | Claude Opus 5.5 | High | 75.52 | #9 |
| 4 | GLM-5.3 | High | 75.22 | #72 |
| 5 | Claude Sonnet 5.5 | High | 74.63 | #24 |
| 6 | GPT-6.1 Sol | High | 73.73 | #15 |
| 7 | GPT-6 Astra | High | 69.55 | #10 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=c2a-bench-support-agent-knowledge · How It Works · Data refreshed daily, snapshot 2026-11-21.