supersededCoding
Terminal-Bench
Metric: Score (higher is better)Superseded by: terminal-bench-2-1
Versionless legacy entry for the Terminal-Bench terminal-agent benchmark maintained by Stanford and the Laude Institute. Superseded for new scores by Terminal-Bench 2.x; kept for historical rows.
Models ranked
2
tracked on this benchmark
Score band
76.2 – 43.2
best → lowest tracked
Snapshot trend
+33.00
May 14 → May 19 · 1 models
Leaderboard
Tracked models ranked by Score (higher is better).
#Model variant and provenanceRelative to leaderScore
1
Gemini 3.5 Flash
76.2Version: Not recordedHarness: Not recordedEvaluator: Not recordedObserved: May 19, 2026Confidence: Not recordedSource
2
Claude 4 Opus
43.2Version: Not recordedHarness: Not recordedEvaluator: Not recordedObserved: May 14, 2025Confidence: Not recordedSource
How to read this benchmark
This benchmark scores models where higher is better. Use scores for directional filtering and shortlisting, not universal quality ranking; then validate pricing, context window, provider availability, and fit for your workload.
Trust this score when
- There is a fresh timestamped snapshot (or multiple snapshots) for this benchmark.
- The model list covers the same version family you can actually deploy today.
- Top candidates overlap with your required routing and feature requirements.
Be cautious when
- There is only one benchmark snapshot or the dataset appears stale.
- The benchmark metric direction is opposite of your decision objective.
- The score difference between options is narrow and likely within implementation variance.
Related benchmarks
Last reviewed: Jun 7, 2026