C2A Bench - Skyway Air (Graph Query): leaderboard

Observe.AI C2A Bench (observeai/c2a-bench) Skyway Air domain (~10,400 to 10,700 docs, 6 stages, 311 graded tickets) using the fixed graph-query agent architecture and fixed openai/gpt-5.6-sol runtime agent. Mean ticket pass rate (0-100%); higher is better.

Metric: Ticket Pass Rate (%). Source: huggingface.co. Saturation forecast: Around February 2027. 6 models tracked. Updated 21 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1Gemini 4 CarbonHigh75.33#7
2Claude Opus 5.5High72.75#9
3GPT-6.1 SolHigh54.75#15
4Claude Sonnet 5.5High49.08#24
5DeepSeek V4.1 Flash (1017)High41.65#47
6GLM-5.3High41.12#72

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-skyway-air-graph-query · How It Works · Data refreshed daily, snapshot 2026-11-21.