Composer 2.5: benchmark results

Provider: Other. Released 2026-05-18. Access: API.

Unified ELO 1712 ± 1, rank #41 of 1392 rated models, from 9 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
BenchmarkList ECI134.11Capability Index (ECI)82.1
Vals AI SWE-bench Verified79.6Resolved (%)71.3
Agent Security League - Functional Correctness75.4Functional Correctness (%)63.9
Vals AI Vibe Code Bench49.61Accuracy (%)59.3
Vals AI Terminal-Bench 2.158.43Accuracy (%)48.4
Agents' Last Exam20.4Pass Rate (%)45.8
Agent Security League - Security Correctness14Security Correctness (%)38.9
CursorBench 3.156.1Score (%)37.7
FrontierSWE34Dominance (%)34.4

Interactive version: theaggregate.ai/model?slug=composer-2-5 · How It Works · Data refreshed daily, snapshot 2026-09-05.