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

#ModelSettingScoreOverall rank
1Gemini 4 CarbonHigh78.51#7
2DeepSeek V4.1 Flash (1017)High76.72#47
3Claude Opus 5.5High75.52#9
4GLM-5.3High75.22#72
5Claude Sonnet 5.5High74.63#24
6GPT-6.1 SolHigh73.73#15
7GPT-6 AstraHigh69.55#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.