Terminal-Bench-Science 0.1 with sixfold verifier timeout (Terminal-Bench-Science 0.1 (6x verifier timeout))
We show this table for reference; we do not rank on it.
Google-run scientific workflow evaluation using a sixfold verifier timeout to address verification timeouts.
Benchmark score on Terminal-Bench-Science 0.1 (6x verifier timeout) — October 17, 2026
We compile the Terminal-Bench-Science 0.1 (6x verifier timeout) rows from provider self-reports. Gemini 4 Argon leads the table at 57.6%. We do not use these results to rank models overall.
1 modelAgenticCurrentDisplay onlyUpdated October 17, 2026
Benchmark score table (1 model)
| Rank | Model / configuration | Score | Parameters (B) | Open / closed |
|---|---|---|---|---|
| 1 | Gemini 4 ArgonGoogle | 57.6% | Not reported | Closed |
How to read this leaderboard
Operator receipt: 1 sourced row is currently displayable on this page; the leading published row is Gemini 4 Argon at 57.6%.
Honest limit: The verifier timeout differs from the standard release; these scores must not replace standard-timeout results.
About Terminal-Bench-Science 0.1 (6x verifier timeout)
Year
2026
Tasks
70 expert-curated scientific research workflows
Format
Resolution rate across 3 trials per task
Difficulty
Frontier scientific research workflows
This launch setup differs from the standard Terminal-Bench-Science 0.1 leaderboard. It stays display-only and is kept on its own key.
Freshness and provenance
Version
Terminal-Bench-Science 0.1 (6x verifier timeout) 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.
Questions
What does Terminal-Bench-Science 0.1 (6x verifier timeout) measure?
Google-run scientific workflow evaluation using a sixfold verifier timeout to address verification timeouts.
Which model scores highest on Terminal-Bench-Science 0.1 (6x verifier timeout)?
Gemini 4 Argon by Google currently leads with a score of 57.6% on Terminal-Bench-Science 0.1 (6x verifier timeout).
How many models are evaluated on Terminal-Bench-Science 0.1 (6x verifier timeout)?
1 AI models have published results on Terminal-Bench-Science 0.1 (6x verifier timeout) in the BenchLM catalog.
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 5,600+ readers.
One email each week. Unsubscribe anytime.