agents benchmark
Connectors
Connectors is an OpenAI internal production benchmark measuring reliable use of connector-based tools in agentic workflows, reported as a pass rate.
Updated Aug 11, 2026
Models3
Model coverage3
MetricScore
EvidenceB
Connectors Ranking
Higher score ranks better on this benchmark.
| 01 | OP | 100.0% | 100.0% | 3 | C | |
| 02 | OP | 100.0% | 50.0% | 3 | C | |
| 03 | OP | 99.9% | 0.0% | 3 | C |
Connectors Score Distribution
A closer view of the leading scores on this benchmark.
Connectors Highlights
The leading models and scores on this benchmark.
What is Connectors?
What Connectors measures and how its scores work.
Connectors is an OpenAI internal production benchmark measuring reliable use of connector-based tools in agentic workflows, reported as a pass rate.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Connectors
- Modality
- text
- Primary category
- agents
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- openai-connectors|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Connectors.
Which model scores highest on Connectors?
GPT-5.6 Sol is currently ranked first with 100.0%.
What does Connectors measure?
Connectors is an OpenAI internal production benchmark measuring reliable use of connector-based tools in agentic workflows, reported as a pass rate.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
3 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.