Coding benchmarks

Claude Opus 5.5 leads revised Artificial Analysis Coding Agent Index

ArtificialAnlys released Coding Agent Index v2.0, with Claude Code running Claude Opus 5.5 leading at 61.7. The account said the index evaluates models together with their harnesses across 290 tasks covering software engineering, terminal use and repository questions.

ArtificialAnlys replaced DeepSWE with FrontierCode v1.1 and revised repository-question grading, reporting lower mean scores under the stricter assessment. teortaxesTex noted that the component benchmarks disagree on rankings and questioned the differing TerminalBench 4.0 results for DeepSeek across Claude Code and Codex.