CITBench - Multi-Step: leaderboard

Metric: Average performance (%; mean Level-Accuracy with partial credit, each of repeated runs scored 0 to 1, on the offline single-turn tabular data processing tasks of CITBench, a balanced 50% slice of its 1,296 instances in 18 matching, cleaning, augmentation and transformation task types; temperature 1.0, 8,192 output tokens; Multi-Step tier: chained operation pipelines). Source: arxiv.org. Saturation forecast: Around December 2026. 12 models tracked.

Top models

#ModelScore
1Claude Sonnet 4.543.52
2DeepSeek V3.241.24
3Gemini 3 Flash40.39
4Gemini 3 Pro38.13
5GPT-5.237.05
6Claude Haiku 4.534.71
7GLM-4.727.06
8Qwen 3 Coder Flash17.9
9Qwen 3 235B A22B17.24
10Qwen 3 32B15.57
11GPT-4o12.93
12Qwen 3 14B4.45

Interactive version: theaggregate.ai/benchmark?slug=citbench-multi-step · How It Works · Data refreshed daily, snapshot 2026-09-26.