Model results

ExploitBench

Choose a shared evaluation protocol to compare model scores. Versions, sources and configurations stay separate.

Atlas snapshot captured 10/19/2026, 10:20:28 AM UTC. This is an import timestamp, not the evaluation date. Coverage may be incomplete.

Official source

← All evaluation groups

ExploitBench

Source: ExploitBench via Epoch AI
Version: v0.1
Measurement date: Not reported
Metric: % · Higher is better
Evaluation scope: Autonudge · result date not supplied

Positions are withheld because at least one result lacks explicit independent provenance or a documented evaluation scope. Missing metadata is shown as unreported; matching imported metadata is not independent verification of the protocol.

Claude Opus 4.7
anthropic/claude-opus-4-7
26.5%
View modelEvidence aggregated
Claude Sonnet 4.6
anthropic/claude-sonnet-4-6
22.7%
View modelEvidence aggregated
Kimi K2.6
moonshotai/kimi-k2.6-20260420
18.4%
View modelEvidence aggregated
GLM 5.1
z-ai/glm-5.1-20260406
18.1%
View modelEvidence aggregated
Gemini 3.1 Pro Preview
google/gemini-3.1-pro-preview-20260219
15.7%
View modelEvidence aggregated
MiniMax M2.7
minimax/minimax-m2.7-20260318
13.3%
View modelEvidence aggregated