Atlas

Benchmarks

← All benchmarks

SRE Bench — Fully Solved

Code · 2026-09-21

Reverse engineering 262 protected binary instances built from 19 in-house programs. Agents use one shell with Ghidra, radare2, GDB, angr and other analysis tools. An instance counts as fully solved only if all six scenario-specific subtasks pass deterministic verification.

Top models (higher is better)

ModelScore
GPT-6 Astra56.9
Claude Opus 5.533.6
GPT-5.6 Sol30.5
Claude Fable 5.122.9
Claude Opus 512.2
Gemini 3.7 Flash4.6
GPT-5.53.8
Hy4 Preview2.3
DeepSeek V4.1 Flash0.8
Grok 4.50.8
GLM-5.20.0
Loading Atlas data…