# Tool Use on BFCL (Live/Non-live/Overall)

Source: [Tool Use on BFCL (Live/Non-live/Overall)](<https://www.sota2.com/research/sota/tool-use-on-bfcl-live-non-live-overall>)

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

Data updated: 2026-03-18T07:41:38.510Z

Evaluation of model performance on general tool utilization capabilities using the BFCL dataset, measured by Live, Non-live, and Overall success rates.

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 | Tool Use |
| Dataset (including any stated split) | BFCL |
| Metric | Live Success Rate |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [Live Success Rate](<https://www.sota2.com/research/sota/tool-use-on-bfcl-live-non-live-overall.md?metric=Live%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Non-live Success Rate](<https://www.sota2.com/research/sota/tool-use-on-bfcl-live-non-live-overall.md?metric=Non-live%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Overall Success Rate](<https://www.sota2.com/research/sota/tool-use-on-bfcl-live-non-live-overall.md?metric=Overall%20Success%20Rate>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Live Success Rate | Result date | Report paper |
| --- | --- | --- | --- |
| CHORD-ϕ | 69.9 | Not recorded | 68fa7bfc1e209131cea8ba85 |
| CHORD-µ | 69.4 | Not recorded | 68fa7bfc1e209131cea8ba85 |
| GRPO | 68.5 | Not recorded | 68fa7bfc1e209131cea8ba85 |
| SFT-best + RL | 67.4 | Not recorded | 68fa7bfc1e209131cea8ba85 |
| LUFFY | 67.2 | Not recorded | 68fa7bfc1e209131cea8ba85 |
| SRFT | 64.6 | Not recorded | 68fa7bfc1e209131cea8ba85 |
| SFT-best | 59.2 | Not recorded | 68fa7bfc1e209131cea8ba85 |

### CHORD-ϕ

Live Success Rate: 69.9. Result ID: 69ba56e647f34ce924a3e19d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bfc1e209131cea8ba85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bfc1e209131cea8ba85.md>)

Recorded evaluation configuration: {"Variant":"ϕ"}. This record does not assert independent reproduction.

### CHORD-µ

Live Success Rate: 69.4. Result ID: 69ba56e647f34ce924a3e19c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bfc1e209131cea8ba85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bfc1e209131cea8ba85.md>)

Recorded evaluation configuration: {"Variant":"µ"}. This record does not assert independent reproduction.

### GRPO

Live Success Rate: 68.5. Result ID: 69ba56e647f34ce924a3e19b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bfc1e209131cea8ba85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73101e209131cea5a395.md>)

[Implementation](<https://github.com/deepseek-ai/DeepSeek-Math>)

Recorded evaluation configuration: {"Mode":"Pure RL"}. This record does not assert independent reproduction.

### SFT-best + RL

Live Success Rate: 67.4. Result ID: 69ba56e647f34ce924a3e19f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bfc1e209131cea8ba85.md>)

Recorded evaluation configuration: {"Type":"SFT and RL"}. This record does not assert independent reproduction.

### LUFFY

Live Success Rate: 67.2. Result ID: 69ba56e647f34ce924a3e1a0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bfc1e209131cea8ba85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79961e209131cea7e682.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### SRFT

Live Success Rate: 64.6. Result ID: 69ba56e647f34ce924a3e1a1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bfc1e209131cea8ba85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79ab1e209131cea7ecd7.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### SFT-best

Live Success Rate: 59.2. Result ID: 69ba56e647f34ce924a3e19e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bfc1e209131cea8ba85.md>)

Recorded evaluation configuration: {"Type":"SFT"}. This record does not assert independent reproduction.

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