reasoning benchmark
Terminal-Bench-Science 0.1 Leaderboard
Terminal-Bench-Science 0.1 is a Stanford-led community benchmark of 70 tasks drawn from scientific research workflows across the life, physical, earth, mathematical, and engineering sciences.
Updated Oct 23, 2026
Models7
Model coverage7
MetricScore
EvidenceB
Terminal-Bench-Science 0.1 Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelOP | Score64.60% | Percentile100.00% | Participants7 | EvidenceC | Evaluated |
| Rank02 | ModelAN | Score59.90% | Percentile83.33% | Participants7 | EvidenceC | Evaluated |
| Rank03 | ModelAN | Score58.70% | Percentile66.67% | Participants7 | EvidenceC | Evaluated |
| Rank04 | ModelGO | Score57.60% | Percentile50.00% | Participants7 | EvidenceC | Evaluated |
| Rank05 | ModelOP | Score57.02% | Percentile33.33% | Participants7 | EvidenceC | Evaluated |
| Rank06 | ModelAN | Score52.60% | Percentile16.67% | Participants7 | EvidenceC | Evaluated |
| Rank07 | ModelAN | Score20.60% | Percentile0.00% | Participants7 | EvidenceC | Evaluated |
Terminal-Bench-Science 0.1 Highlights
The leading models and scores on this benchmark.
Terminal-Bench-Science 0.1 Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for Terminal-Bench-Science 0.1
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is Terminal-Bench-Science 0.1?
What Terminal-Bench-Science 0.1 measures and how its scores work.
It is a reasoning benchmark whose tasks are authored and reviewed by scientists and researchers.
It reports a Score in ratio units, typically as accuracy across the benchmark tasks.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Terminal-Bench-Science 0.1
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Terminal-Bench-Science 0.1.
Which model scores highest on Terminal-Bench-Science 0.1?
GPT-6 Astra is currently ranked first with 64.60%.
What are the top three models on Terminal-Bench-Science 0.1?
The current leaders are GPT-6 Astra (64.60%), Claude Sonnet 5.5 (59.90%), and Claude Opus 5.5 (58.70%).
Which Terminal-Bench-Science 0.1 model has the lowest official input price?
Claude Haiku 5.5 has the lowest matched official input price at $0.10 input / $0.50 output per 1M tokens.
Which models are fastest among Terminal-Bench-Science 0.1 results?
The fastest matched records are Claude Sonnet 5.5 (42.00 tok/s via Anthropic) and Claude Opus 5.5 (12.33 tok/s via Anthropic).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.