# Dialogue State Transition on PFDial OOD (test)

Source: [Dialogue State Transition on PFDial OOD (test)](<https://www.sota2.com/research/sota/dialogue-state-transition-on-pfdial-ood-test>)

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

Data updated: 2026-02-26T05:26:45.243Z

Evaluation of Dialogue State Transition performance on the Out-of-Distribution (OOD) test split of the PFDial dataset, measured using accuracy metrics like Sequential Acc and Decision Acc.

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 | Dialogue State Transition |
| Dataset (including any stated split) | PFDial OOD (test) |
| Metric | Acc |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| 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

- [Acc](<https://www.sota2.com/research/sota/dialogue-state-transition-on-pfdial-ood-test.md?metric=Acc>): Higher is better; unit: PERCENT.

- [Decision Acc](<https://www.sota2.com/research/sota/dialogue-state-transition-on-pfdial-ood-test.md?metric=Decision%20Acc>): Higher is better; unit: PERCENT.

- [Sequential Acc](<https://www.sota2.com/research/sota/dialogue-state-transition-on-pfdial-ood-test.md?metric=Sequential%20Acc>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Acc | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen2.5-7B | 96.31 | Not recorded | 68fa79591e209131cea7d332 |
| Qwen2.5-3B | 94.57 | Not recorded | 68fa79591e209131cea7d332 |
| Qwen2.5-1.5B | 93.87 | Not recorded | 68fa79591e209131cea7d332 |
| Qwen2.5-0.5B | 92.76 | Not recorded | 68fa79591e209131cea7d332 |
| Qwen2.5-1.5B | 87.9 | Not recorded | 68fa79591e209131cea7d332 |
| GPT-4o | 86.29 | Not recorded | 68fa79591e209131cea7d332 |
| GPT-3.5-Turbo | 79.76 | Not recorded | 68fa79591e209131cea7d332 |
| Qwen2.5-3B | 79.73 | Not recorded | 68fa79591e209131cea7d332 |
| DeepSeek-v3 | 79.02 | Not recorded | 68fa79591e209131cea7d332 |
| Qwen2.5-7B | 76.04 | Not recorded | 68fa79591e209131cea7d332 |
| Gemini-2.0-Flash-Exp | 75.17 | Not recorded | 68fa79591e209131cea7d332 |
| Qwen2.5-7B-Instruct | 65.87 | Not recorded | 68fa79591e209131cea7d332 |
| Claude-3.5-Sonnet | 62.74 | Not recorded | 68fa79591e209131cea7d332 |
| Qwen2.5-0.5B | 50.77 | Not recorded | 68fa79591e209131cea7d332 |
| LLaMA-3.1-8B-Instruct | 13.2 | Not recorded | 68fa79591e209131cea7d332 |

### Qwen2.5-7B

Acc: 96.31. Result ID: 6995db603badfaffe6e1e54c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79591e209131cea7d332.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79591e209131cea7d332.md>)

[Implementation](<https://github.com/KongLongGeFDU/PFDial>)

Recorded evaluation configuration: {"Training Approach":"Integrated Training"}. This record does not assert independent reproduction.

### Qwen2.5-3B

Acc: 94.57. Result ID: 6995db603badfaffe6e1e54b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79591e209131cea7d332.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79591e209131cea7d332.md>)

[Implementation](<https://github.com/KongLongGeFDU/PFDial>)

Recorded evaluation configuration: {"Training Approach":"Integrated Training"}. This record does not assert independent reproduction.

### Qwen2.5-1.5B

Acc: 93.87. Result ID: 6995db603badfaffe6e1e54a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79591e209131cea7d332.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79591e209131cea7d332.md>)

[Implementation](<https://github.com/KongLongGeFDU/PFDial>)

Recorded evaluation configuration: {"Training Approach":"Integrated Training"}. This record does not assert independent reproduction.

### Qwen2.5-0.5B

Acc: 92.76. Result ID: 6995db603badfaffe6e1e549.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79591e209131cea7d332.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79591e209131cea7d332.md>)

[Implementation](<https://github.com/KongLongGeFDU/PFDial>)

Recorded evaluation configuration: {"Training Approach":"Integrated Training"}. This record does not assert independent reproduction.

### Qwen2.5-1.5B

Acc: 87.9. Result ID: 6995db603badfaffe6e1e546.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79591e209131cea7d332.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79591e209131cea7d332.md>)

[Implementation](<https://github.com/KongLongGeFDU/PFDial>)

Recorded evaluation configuration: {"Training Approach":"Secondary Fine-tuning"}. This record does not assert independent reproduction.

### GPT-4o

Acc: 86.29. Result ID: 6995db603badfaffe6e1e544.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79591e209131cea7d332.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa727a1e209131cea56a1e.md>)

[Implementation](<https://github.com/openai/evals>)

Recorded evaluation configuration: {"Training Approach":"Baselines"}. This record does not assert independent reproduction.

### GPT-3.5-Turbo

Acc: 79.76. Result ID: 6995db603badfaffe6e1e543.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79591e209131cea7d332.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bf71e209131cea314c0.md>)

[Implementation](<https://github.com/openai/following-instructions-human-feedback>)

Recorded evaluation configuration: {"Training Approach":"Baselines"}. This record does not assert independent reproduction.

### Qwen2.5-3B

Acc: 79.73. Result ID: 6995db603badfaffe6e1e547.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79591e209131cea7d332.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79591e209131cea7d332.md>)

[Implementation](<https://github.com/KongLongGeFDU/PFDial>)

Recorded evaluation configuration: {"Training Approach":"Secondary Fine-tuning"}. This record does not assert independent reproduction.

### DeepSeek-v3

Acc: 79.02. Result ID: 6995db603badfaffe6e1e542.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79591e209131cea7d332.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77001e209131cea7066a.md>)

Recorded evaluation configuration: {"Training Approach":"Baselines"}. This record does not assert independent reproduction.

### Qwen2.5-7B

Acc: 76.04. Result ID: 6995db603badfaffe6e1e548.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79591e209131cea7d332.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79591e209131cea7d332.md>)

[Implementation](<https://github.com/KongLongGeFDU/PFDial>)

Recorded evaluation configuration: {"Training Approach":"Secondary Fine-tuning"}. This record does not assert independent reproduction.

### Gemini-2.0-Flash-Exp

Acc: 75.17. Result ID: 6995db603badfaffe6e1e541.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79591e209131cea7d332.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78731e209131cea78622.md>)

Recorded evaluation configuration: {"Training Approach":"Baselines"}. This record does not assert independent reproduction.

### Qwen2.5-7B-Instruct

Acc: 65.87. Result ID: 6995db603badfaffe6e1e540.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79591e209131cea7d332.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa767e1e209131cea6d6a7.md>)

Recorded evaluation configuration: {"Training Approach":"Baselines"}. This record does not assert independent reproduction.

### Claude-3.5-Sonnet

Acc: 62.74. Result ID: 6995db603badfaffe6e1e53f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79591e209131cea7d332.md>)

Recorded evaluation configuration: {"Training Approach":"Baselines"}. This record does not assert independent reproduction.

### Qwen2.5-0.5B

Acc: 50.77. Result ID: 6995db603badfaffe6e1e545.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79591e209131cea7d332.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79591e209131cea7d332.md>)

[Implementation](<https://github.com/KongLongGeFDU/PFDial>)

Recorded evaluation configuration: {"Training Approach":"Secondary Fine-tuning"}. This record does not assert independent reproduction.

### LLaMA-3.1-8B-Instruct

Acc: 13.2. Result ID: 6995db603badfaffe6e1e53e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79591e209131cea7d332.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a028.md>)

[Implementation](<https://github.com/meta-llama/llama-agentic-system>)

Recorded evaluation configuration: {"Training Approach":"Baselines"}. This record does not assert independent reproduction.

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