evals.report
BenchmarksLabsCompareRun guidesIn the wild

Gemini CLI + Gemini 3.1 Pro

Agent systems · Agent.

Gemini CLI + Gemini 3.1 Pro is a model from Agent systems in the Agent family. evals.report tracks 2 reported Gemini CLI + Gemini 3.1 Pro benchmark scores across Terminal-Bench 2.1, SWE-Marathon — each shown with its benchmark, metric, source status, and date, and never combined into a single ranking.

2 results

Benchmark results 2

Compare this model
BenchmarkCategoryScoreMetricStatusDate
Terminal-Bench 2.1Agents70.7%task successVerifiedDetails
SWE-MarathonAgents2.0%resolution rate (pass@1)OfficialDetails