E-Bench-Code: leaderboard
E-Bench (Tencent Hunyuan, 2026) builds synthetic product environments modelled on Honor of Kings, QQ Music and Tencent Meeting with 323 state-changing tasks that require discovering hidden data and composing several tool calls, graded by exact database-state diff over three trials per task. In E-Bench-Code the agent also has an exec_code tool; score is Avg@3 in percent, higher is better.
Metric: Avg@3 (%; per-trial success averaged over tasks and three trials; domain MCP tools plus an exec_code tool) 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 February 2027. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.8 (Max) | 81.11 | #56 (Claude Opus 4.8) |
| 2 | Kimi K3 (Max) | 77.61 | #54 (Kimi K3) |
| 3 | GPT-5.5 (xHigh) | 77.19 | #49 (GPT-5.5) |
| 4 | Grok 4.5 (High) | 69.24 | #82 (Grok 4.5) |
| 5 | Hy3 | 64.4 | #195 |
| 6 | Gemini 3.5 Flash (High) | 62.54 | #101 (Gemini 3.5 Flash) |
| 7 | Qwen 3.7 Max | 61.92 | #145 |
| 8 | GLM-5.2 (Max) | 60.99 | #138 (GLM-5.2) |
| 9 | Seed 2.1 Pro | 53.04 | #135 |
| 10 | DeepSeek V4 Pro (Max) | 47.68 | #188 (DeepSeek V4 Pro) |
| 11 | MiniMax-M3 | 46.85 | #269 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=e-bench-code · How It Works · Data refreshed daily, snapshot 2026-11-13.