evals.report
BenchmarksLabsCompareRun guidesIn the wild

Claude Code + Claude Opus 4.8

Agent systems · Agent.

Claude Code + Claude Opus 4.8 is a model from Agent systems in the Agent family. evals.report tracks 3 reported Claude Code + Claude Opus 4.8 benchmark scores across Terminal-Bench 4.0, Terminal-Bench 2.1, SWE-Marathon — each shown with its benchmark, metric, source status, and date, and never combined into a single ranking.

3 results

Benchmark results 3

Compare this model
BenchmarkCategoryScoreMetricStatusDate
Terminal-Bench 4.0Agents23.6%resolution rateOfficialDetails
Terminal-Bench 2.1Agents78.9%task successVerifiedDetails
SWE-MarathonAgents26.0%resolution rate (pass@1)OfficialDetails