# Agentic Function Calling on BFCL v3 (val)

Source: [Agentic Function Calling on BFCL v3 (val)](<https://www.sota2.com/research/sota/agentic-function-calling-on-bfcl-v3-val>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-13T07:33:36.846Z

Evaluation of Agentic Function Calling performance on the validation split of the BFCL v3 dataset, reporting specialized metrics including Base, Miss-F, Miss-P, Long, Comp., and Overall scores.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Agentic function-calling |
| Dataset (including any stated split) | BFCL v3 (val) |
| Metric | Base Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Base Score](<https://www.sota2.com/research/sota/agentic-function-calling-on-bfcl-v3-val.md?metric=Base%20Score>): Higher is better; unit: PERCENT.

- [Miss-F Score](<https://www.sota2.com/research/sota/agentic-function-calling-on-bfcl-v3-val.md?metric=Miss-F%20Score>): Higher is better; unit: PERCENT.

- [Miss-P Score](<https://www.sota2.com/research/sota/agentic-function-calling-on-bfcl-v3-val.md?metric=Miss-P%20Score>): Higher is better; unit: PERCENT.

- [Long Context Score](<https://www.sota2.com/research/sota/agentic-function-calling-on-bfcl-v3-val.md?metric=Long%20Context%20Score>): Higher is better; unit: PERCENT.

- [Complexity Score](<https://www.sota2.com/research/sota/agentic-function-calling-on-bfcl-v3-val.md?metric=Complexity%20Score>): Higher is better; unit: PERCENT.

- [Overall Score](<https://www.sota2.com/research/sota/agentic-function-calling-on-bfcl-v3-val.md?metric=Overall%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Base Score | Result date | Report paper |
| --- | --- | --- | --- |
| METIS | 54.2 | Not recorded | 6a04057ddbc836b87d827475 |
| No Curriculum | 50.6 | Not recorded | 6a04057ddbc836b87d827475 |

### METIS

Base Score: 54.2. Result ID: 6a0428e347f34ce924e9b4b7.

[Reporting paper](<https://www.sota2.com/research/paper/6a04057ddbc836b87d827475.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a04057ddbc836b87d827475.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-4B-Instruct","Training Algorithm":"GRPO","Evaluation Protocol":"mean@8","Time":"4.9"}. This record does not assert independent reproduction.

### No Curriculum

Base Score: 50.6. Result ID: 6a0428e347f34ce924e9b4b6.

[Reporting paper](<https://www.sota2.com/research/paper/6a04057ddbc836b87d827475.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-4B-Instruct","Training Algorithm":"GRPO","Evaluation Protocol":"mean@8","Time":"4.2"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
