Benchmark profile
Terminal-Bench 2.1 (provider run) (Terminal-Bench 2.1)
A provider-run Terminal-Bench 2.1 result stored separately from the repository's Terminal-Bench 2.0 lane.
Data verifiedBenchmark score on Terminal-Bench 2.1 — July 31, 2026
BenchLM mirrors the published score view for Terminal-Bench 2.1. DeepSeek V4 Flash (Max) leads the public snapshot at 82.7%. BenchLM does not use these results to rank models overall.
Benchmark score table (1 model)
ScoreAbout Terminal-Bench 2.1
Year
2026
Tasks
Terminal-based software-agent tasks
Format
Interactive task success rate
Difficulty
Professional software engineering
DeepSeek reports this value at max effort using its upcoming harness in minimal mode. BenchLM keeps it display-only because the version and agent harness differ from the weighted Terminal-Bench 2.0 field.
BenchLM freshness & provenance
Version
Terminal-Bench 2.1 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
FAQ
What does Terminal-Bench 2.1 measure?
A provider-run Terminal-Bench 2.1 result stored separately from the repository's Terminal-Bench 2.0 lane.
Which model scores highest on Terminal-Bench 2.1?
DeepSeek V4 Flash (Max) by DeepSeek currently leads with a score of 82.7% on Terminal-Bench 2.1.
How many models are evaluated on Terminal-Bench 2.1?
1 AI models have been evaluated on Terminal-Bench 2.1 on BenchLM.
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 2,000+ readers.
One email each week. Unsubscribe anytime.