agents benchmark
Search and Function-Calling
Search and Function-Calling is an OpenAI internal production benchmark measuring reliable search-tool use and function calling in agentic workflows, reported as a pass rate.
Updated Aug 7, 2026
Published models3
Registry coverage3
MetricScore
EvidenceB
Search and Function-Calling leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | OP | 94.6% | 100.0% | 3 | C | |
| 2 | OP | 91.0% | 50.0% | 3 | C | |
| 3 | OP | 89.7% | 0.0% | 3 | C |
Score distribution
Top published rows on the benchmark's original scale.
Search and Function-Calling highlights
The top published results on this benchmark's own scale.
What is Search and Function-Calling?
Definition and scoring fields from the benchmark registry.
Search and Function-Calling is an OpenAI internal production benchmark measuring reliable search-tool use and function calling in agentic workflows, reported as a pass rate.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- Search and Function-Calling
- Modality
- text
- Primary category
- agents
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- openai-search-function-calling|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about Search and Function-Calling.
Which model scores highest on Search and Function-Calling?
GPT-5.6 Terra is currently ranked first with 94.6%.
What does Search and Function-Calling measure?
Search and Function-Calling is an OpenAI internal production benchmark measuring reliable search-tool use and function calling 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 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.