KAware - Hybrid Composition Pass Rate: leaderboard
Metric: The end-to-end pass rate (%): share of tasks whose trajectory and final answer a gpt-4.1 judge marks correct, on the hybrid composition 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: Estimated already saturated. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 (Thinking) | 98.97 |
| 2 | Qwen 3 Max (Preview) | 97.01 |
| 3 | Qwen 3.5 397B A17B | 93.75 |
| 4 | Gemini 3 Pro (Preview) | 88.86 |
| 5 | Qwen 3.5 397B A17B (Non-reasoning) | 88.32 |
| 6 | Qwen 3 235B A22B 2507 Instruct | 86.96 |
| 7 | DeepSeek V4 Flash (Non-reasoning) | 85.6 |
| 8 | GPT-5.5 | 84.78 |
| 9 | Qwen 3 235B A22B 2507 (Thinking) | 83.89 |
| 10 | DeepSeek V3.2 (Non-reasoning) | 77.45 |
| 11 | Claude Sonnet 4.5 | 74.73 |
| 12 | GPT-4o (2024-11-20) | 65.49 |
| 13 | GPT-4.1 | 64.95 |
| 14 | Gemini 3 Flash (Preview) | 64.95 |
| 15 | GPT-5 | 63.32 |
Interactive version: theaggregate.ai/benchmark?slug=kaware-hybrid-composition-pass-rate · How It Works · Data refreshed daily, snapshot 2026-09-29.