KAware - Internal Function: leaderboard

Metric: The knowing-acting score (%, KAS): harmonic mean of knowing accuracy (Jaccard overlap between the tools the agent says the task needs and the gold tool set) and acting accuracy (Jaccard overlap between the tools it actually calls and the gold set), on the internal function setting, on the KAware tool-use tasks, where tools are always available but the task may need them (external function, 310 tasks), mix them with parametric knowledge (hybrid composition, 368 tasks) or be solvable from knowledge alone (internal function, 398 tasks); higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 18 models tracked.

Top models

#ModelScore
1GPT-572.22
2O4 Mini (2025-04-16)57.41
3GPT-5.544.15
4Gemini 3 Pro (Preview)38.83
5GPT-4.135.98
6DeepSeek R1 052835.68
7Gemini 3 Flash (Preview)33.24
8GPT-4o (2024-11-20)31.98
9Qwen 3.5 397B A17B28.67
10Qwen 3.5 397B A17B (Non-reasoning)28.13
11Claude Sonnet 4.525.7
12DeepSeek V4 Flash (Non-reasoning)21.89
13Claude Sonnet 4.5 (Thinking)21.84
14Qwen 3 235B A22B 2507 (Thinking)21.4
15DeepSeek V3.2 (Non-reasoning)16.54

Interactive version: theaggregate.ai/benchmark?slug=kaware-internal-function · How It Works · Data refreshed daily, snapshot 2026-09-29.