Codesota · Models · Terminus-KIRA / Gemini 3.1 ProTerminus-KIRA1 results · 1 benchmarks
Model card

Terminus-KIRA / Gemini 3.1 Pro.

Terminus-KIRAapi

Terminal-Bench 2.0 leaderboard system. Treat as an agent/model system, not a raw base model.

§ 02 · Benchmarks

Every benchmark Terminus-KIRA / Gemini 3.1 Pro has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01Terminal-Bench 2.0Agentic AI · Autonomous Codingaccuracy74.8%#10/202026-04-27source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area

Where Terminus-KIRA / Gemini 3.1 Pro actually performs.

Agentic AI
1
benchmark
avg rank #10.0
§ 05 · Related models

Other Terminus-KIRA models scored on Codesota.

Terminus-KIRA / Claude Opus 4.6
1 result
§ 06 · Sources & freshness

Where these numbers come from.

terminal-bench-official
1
result
1 of 1 rows marked verified.