E-Bench: leaderboard

Metric: Avg@3 (%; per-trial success averaged over tasks and three trials; domain MCP tools only) on 323 synthetic state-changing tasks in three product environments (Honor of Kings, QQ Music, Tencent Meeting), graded by exact database-state diff; three trials per task, each model at its highest available thinking effort in a shared MCP harness. Source: arxiv.org. Saturation forecast: Around December 2026. 11 models tracked.

Top models

#ModelScore
1Kimi K3 (Max)73.79
2GPT-5.5 (xHigh)72.03
3Claude Opus 4.8 (Max)68.78
4Grok 4.5 (High)66.1
5GLM-5.2 (Max)52.32
6Qwen 3.7 Max50.88
7Hy350.15
8Seed 2.1 Pro47.94
9Gemini 3.5 Flash (High)42.62
10MiniMax-M341.07
11DeepSeek V4 Pro (Max)34.47

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