# Proactive Action Prediction on ABCD+

Source: [Proactive Action Prediction on ABCD+](<https://www.sota2.com/research/sota/proactive-action-prediction-on-abcd-plus>)

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

Data updated: 2026-05-26T09:28:44.376Z

Evaluation of Proactive Action Prediction performance on the ABCD+ dataset, measured using metrics like PRI, AC, and Fault Trigger Rate.

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 | Proactive Action Prediction |
| Dataset (including any stated split) | ABCD+ |
| Metric | PRI |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 34 of 34 |
| 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

- [PRI](<https://www.sota2.com/research/sota/proactive-action-prediction-on-abcd-plus.md?metric=PRI>): Higher is better; unit: SCALAR.

- [AC](<https://www.sota2.com/research/sota/proactive-action-prediction-on-abcd-plus.md?metric=AC>): Higher is better; unit: SCALAR.

- [Max AC](<https://www.sota2.com/research/sota/proactive-action-prediction-on-abcd-plus.md?metric=Max%20AC>): Higher is better; unit: SCALAR.

- [Difference](<https://www.sota2.com/research/sota/proactive-action-prediction-on-abcd-plus.md?metric=Difference>): Lower is better; unit: SCALAR.

- [Proactive Timing](<https://www.sota2.com/research/sota/proactive-action-prediction-on-abcd-plus.md?metric=Proactive%20Timing>): Lower is better; unit: TIME.

- [Fault Trigger Rate](<https://www.sota2.com/research/sota/proactive-action-prediction-on-abcd-plus.md?metric=Fault%20Trigger%20Rate>): Lower is better; unit: PERCENT.

- [Ready Action Rate](<https://www.sota2.com/research/sota/proactive-action-prediction-on-abcd-plus.md?metric=Ready%20Action%20Rate>): Higher is better; unit: PERCENT.

## Recorded results

| Method | PRI | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen2.5-14B-ProActor-Q4 | 0.7293 | Not recorded | 6a152914dbd7150506f7deaa |
| Qwen2.5-14B-ProActor-Q4 | 0.7293 | Not recorded | 6a152914dbd7150506f7deaa |
| Qwen2.5-14B-ProActor-Q4 | 0.6842 | Not recorded | 6a152914dbd7150506f7deaa |
| Qwen2.5-14B-ProActor-Q4 | 0.6842 | Not recorded | 6a152914dbd7150506f7deaa |
| Claude-4 | 0.6318 | Not recorded | 6a152914dbd7150506f7deaa |
| Claude-4 | 0.6318 | Not recorded | 6a152914dbd7150506f7deaa |
| Gemini-2.5-flash | 0.6251 | Not recorded | 6a152914dbd7150506f7deaa |
| Gemini-2.5-flash | 0.6251 | Not recorded | 6a152914dbd7150506f7deaa |
| Qwen2.5-14B-Instruct | 0.6246 | Not recorded | 6a152914dbd7150506f7deaa |
| Qwen2.5-14B-Instruct | 0.6246 | Not recorded | 6a152914dbd7150506f7deaa |
| Gemini-2.5-flash | 0.6216 | Not recorded | 6a152914dbd7150506f7deaa |
| Claude-4 | 0.6216 | Not recorded | 6a152914dbd7150506f7deaa |
| Gemini-2.5-flash | 0.6216 | Not recorded | 6a152914dbd7150506f7deaa |
| Claude-4 | 0.6216 | Not recorded | 6a152914dbd7150506f7deaa |
| Claude-4 | 0.6031 | Not recorded | 6a152914dbd7150506f7deaa |
| Claude-4 | 0.6031 | Not recorded | 6a152914dbd7150506f7deaa |
| GPT-5.1 | 0.6003 | Not recorded | 6a152914dbd7150506f7deaa |
| GPT-5.1 | 0.6003 | Not recorded | 6a152914dbd7150506f7deaa |
| Qwen2.5-14B-Instruct | 0.5553 | Not recorded | 6a152914dbd7150506f7deaa |
| GPT-5.1 | 0.5547 | Not recorded | 6a152914dbd7150506f7deaa |
| GPT-5.1 | 0.5547 | Not recorded | 6a152914dbd7150506f7deaa |
| Gemini-2.5-flash | 0.5257 | Not recorded | 6a152914dbd7150506f7deaa |
| Gemini-2.5-flash | 0.5257 | Not recorded | 6a152914dbd7150506f7deaa |
| GPT-5.1 | 0.5104 | Not recorded | 6a152914dbd7150506f7deaa |
| GPT-5.1 | 0.5104 | Not recorded | 6a152914dbd7150506f7deaa |
| GPT-4.1-mini | 0.4405 | Not recorded | 6a152914dbd7150506f7deaa |
| Qwen2.5-14B-Instruct | 0.4331 | Not recorded | 6a152914dbd7150506f7deaa |
| Qwen2.5-14B-Instruct | 0.4331 | Not recorded | 6a152914dbd7150506f7deaa |
| GPT-4.1-mini | 0.4092 | Not recorded | 6a152914dbd7150506f7deaa |
| GPT-4.1-mini | 0.3986 | Not recorded | 6a152914dbd7150506f7deaa |
| Qwen2.5-14B-Instruct | 0.2996 | Not recorded | 6a152914dbd7150506f7deaa |
| Qwen2.5-14B-Instruct | 0.2996 | Not recorded | 6a152914dbd7150506f7deaa |
| Qwen2.5-14B-Instruct | 0.17 | Not recorded | 6a152914dbd7150506f7deaa |
| Qwen2.5-14B-Instruct | 0.17 | Not recorded | 6a152914dbd7150506f7deaa |

### Qwen2.5-14B-ProActor-Q4

PRI: 0.7293. Result ID: 6a156782fbc373592c0d27e7.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"RULER":"Custom"}. This record does not assert independent reproduction.

### Qwen2.5-14B-ProActor-Q4

PRI: 0.7293. Result ID: 6a156782fbc373592c0d2807.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"RULER":"Custom"}. This record does not assert independent reproduction.

### Qwen2.5-14B-ProActor-Q4

PRI: 0.6842. Result ID: 6a156782fbc373592c0d27e8.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"RULER":"Adaptive"}. This record does not assert independent reproduction.

### Qwen2.5-14B-ProActor-Q4

PRI: 0.6842. Result ID: 6a156782fbc373592c0d2808.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"RULER":"Adaptive"}. This record does not assert independent reproduction.

### Claude-4

PRI: 0.6318. Result ID: 6a156782fbc373592c0d27e0.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"Reasoning":"true"}. This record does not assert independent reproduction.

### Claude-4

PRI: 0.6318. Result ID: 6a156782fbc373592c0d2801.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"Reasoning":"true","ASG":"false"}. This record does not assert independent reproduction.

### Gemini-2.5-flash

PRI: 0.6251. Result ID: 6a156782fbc373592c0d27dc.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"Reasoning":"false"}. This record does not assert independent reproduction.

### Gemini-2.5-flash

PRI: 0.6251. Result ID: 6a156782fbc373592c0d27fd.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"Reasoning":"false","ASG":"false"}. This record does not assert independent reproduction.

### Qwen2.5-14B-Instruct

PRI: 0.6246. Result ID: 6a156782fbc373592c0d27e3.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"Reasoning":"true"}. This record does not assert independent reproduction.

### Qwen2.5-14B-Instruct

PRI: 0.6246. Result ID: 6a156782fbc373592c0d2804.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"Reasoning":"true","ASG":"false"}. This record does not assert independent reproduction.

### Gemini-2.5-flash

PRI: 0.6216. Result ID: 6a156782fbc373592c0d27dd.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"Reasoning":"true"}. This record does not assert independent reproduction.

### Claude-4

PRI: 0.6216. Result ID: 6a156782fbc373592c0d27df.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"Reasoning":"false"}. This record does not assert independent reproduction.

### Gemini-2.5-flash

PRI: 0.6216. Result ID: 6a156782fbc373592c0d27fe.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"Reasoning":"true","ASG":"false"}. This record does not assert independent reproduction.

### Claude-4

PRI: 0.6216. Result ID: 6a156782fbc373592c0d2800.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"Reasoning":"false","ASG":"false"}. This record does not assert independent reproduction.

### Claude-4

PRI: 0.6031. Result ID: 6a156782fbc373592c0d27e1.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"Reasoning":"true","ASG":"true"}. This record does not assert independent reproduction.

### Claude-4

PRI: 0.6031. Result ID: 6a156782fbc373592c0d2802.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"Reasoning":"true","ASG":"true"}. This record does not assert independent reproduction.

### GPT-5.1

PRI: 0.6003. Result ID: 6a156782fbc373592c0d27da.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"Reasoning":"true"}. This record does not assert independent reproduction.

### GPT-5.1

PRI: 0.6003. Result ID: 6a156782fbc373592c0d27fb.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"Reasoning":"true","ASG":"false"}. This record does not assert independent reproduction.

### Qwen2.5-14B-Instruct

PRI: 0.5553. Result ID: 6a156782fbc373592c0d27e6.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"mode":"SFT (Full-tune)"}. This record does not assert independent reproduction.

### GPT-5.1

PRI: 0.5547. Result ID: 6a156782fbc373592c0d27db.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"Reasoning":"true","ASG":"true"}. This record does not assert independent reproduction.

### GPT-5.1

PRI: 0.5547. Result ID: 6a156782fbc373592c0d27fc.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"Reasoning":"true","ASG":"true"}. This record does not assert independent reproduction.

### Gemini-2.5-flash

PRI: 0.5257. Result ID: 6a156782fbc373592c0d27de.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"Reasoning":"true","ASG":"true"}. This record does not assert independent reproduction.

### Gemini-2.5-flash

PRI: 0.5257. Result ID: 6a156782fbc373592c0d27ff.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"Reasoning":"true","ASG":"true"}. This record does not assert independent reproduction.

### GPT-5.1

PRI: 0.5104. Result ID: 6a156782fbc373592c0d27d9.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"Reasoning":"false"}. This record does not assert independent reproduction.

### GPT-5.1

PRI: 0.5104. Result ID: 6a156782fbc373592c0d27fa.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"Reasoning":"false","ASG":"false"}. This record does not assert independent reproduction.

### GPT-4.1-mini

PRI: 0.4405. Result ID: 6a156782fbc373592c0d27d6.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"Reasoning":"false"}. This record does not assert independent reproduction.

### Qwen2.5-14B-Instruct

PRI: 0.4331. Result ID: 6a156782fbc373592c0d27e4.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"Reasoning":"true","ASG":"true"}. This record does not assert independent reproduction.

### Qwen2.5-14B-Instruct

PRI: 0.4331. Result ID: 6a156782fbc373592c0d2805.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"Reasoning":"true","ASG":"true"}. This record does not assert independent reproduction.

### GPT-4.1-mini

PRI: 0.4092. Result ID: 6a156782fbc373592c0d27d8.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"Reasoning":"true","ASG":"true"}. This record does not assert independent reproduction.

### GPT-4.1-mini

PRI: 0.3986. Result ID: 6a156782fbc373592c0d27d7.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"Reasoning":"true"}. This record does not assert independent reproduction.

### Qwen2.5-14B-Instruct

PRI: 0.2996. Result ID: 6a156782fbc373592c0d27e2.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"Reasoning":"false"}. This record does not assert independent reproduction.

### Qwen2.5-14B-Instruct

PRI: 0.2996. Result ID: 6a156782fbc373592c0d2803.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"Reasoning":"false","ASG":"false"}. This record does not assert independent reproduction.

### Qwen2.5-14B-Instruct

PRI: 0.17. Result ID: 6a156782fbc373592c0d27e5.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

Recorded evaluation configuration: {"mode":"SFT (LoRA)"}. This record does not assert independent reproduction.

### Qwen2.5-14B-Instruct

PRI: 0.17. Result ID: 6a156782fbc373592c0d2806.

[Reporting paper](<https://www.sota2.com/research/paper/6a152914dbd7150506f7deaa.md>)

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

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