Ko-AgentBench - L4 Parallel Tool Reasoning — leaderboard
Metric: Coverage (%). Source: huggingface.co. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 | 75 |
| 2 | Claude Haiku 4.5 | 75 |
| 3 | GPT-4o | 71.67 |
| 4 | Qwen 3 Next 80B A3B | 70 |
| 5 | DeepSeek V3.1 | 66.67 |
| 6 | nova-2-lite-v1 | 65 |
| 7 | GPT-4o Mini | 58.33 |
| 8 | Grok 4.1 Fast | 56.67 |
| 9 | GPT-5 | 55 |
| 10 | Gemini 2.5 Pro | 46.67 |
| 11 | GPT-5 Mini | 36.67 |
| 12 | Gemini 2.5 Flash | 35 |
| 13 | Gemini 2.5 Flash Lite | 35 |
Interactive version: aibenchmarks.dev/benchmark?slug=ko-agentbench-l4-parallel-tool-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-17.