# Behavioral Dialogue Evaluation on LifeSim (test)

Source: [Behavioral Dialogue Evaluation on LifeSim (test)](<https://www.sota2.com/research/sota/behavioral-dialogue-evaluation-on-lifesim-test>)

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

Data updated: 2026-03-13T09:27:39.616Z

Evaluation of behavioral dialogue performance on the test split of the LifeSim dataset, focusing on metrics like Proactive Inquiry and Rigid Reasoning.

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 | Behavioral Dialogue Evaluation |
| Dataset (including any stated split) | LifeSim (test) |
| Metric | Proactive Inquiry |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 14 of 14 |
| 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

- [Proactive Inquiry](<https://www.sota2.com/research/sota/behavioral-dialogue-evaluation-on-lifesim-test.md?metric=Proactive%20Inquiry>): Higher is better; unit: PERCENT.

- [Rigid Reasoning](<https://www.sota2.com/research/sota/behavioral-dialogue-evaluation-on-lifesim-test.md?metric=Rigid%20Reasoning>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Proactive Inquiry | Result date | Report paper |
| --- | --- | --- | --- |
| Claude-Sonnet-4.5 | 51.2 | Not recorded | 69b39a320636e5bf4afbcc8e |
| Gemma3-it 27B | 34.2 | Not recorded | 69b39a320636e5bf4afbcc8e |
| DeepSeek-V3.2 Thinking | 29.2 | Not recorded | 69b39a320636e5bf4afbcc8e |
| Llama3.1-70B-it | 22.4 | Not recorded | 69b39a320636e5bf4afbcc8e |
| DeepSeek-V3.2 | 20.9 | Not recorded | 69b39a320636e5bf4afbcc8e |
| GPT-5 | 16.6 | Not recorded | 69b39a320636e5bf4afbcc8e |
| GPT-4o | 16.5 | Not recorded | 69b39a320636e5bf4afbcc8e |
| Gemma3-it 12B | 13.7 | Not recorded | 69b39a320636e5bf4afbcc8e |
| Llama3.1-8B-it | 12.6 | Not recorded | 69b39a320636e5bf4afbcc8e |
| Qwen3-it 32B | 9.8 | Not recorded | 69b39a320636e5bf4afbcc8e |
| Qwen3-it 8B | 5.1 | Not recorded | 69b39a320636e5bf4afbcc8e |
| Qwen3-it 14B | 4.9 | Not recorded | 69b39a320636e5bf4afbcc8e |
| GPT-oss-20B | 2 | Not recorded | 69b39a320636e5bf4afbcc8e |
| GPT-oss-120B | 1.7 | Not recorded | 69b39a320636e5bf4afbcc8e |

### Claude-Sonnet-4.5

Proactive Inquiry: 51.2. Result ID: 69b3d87847f34ce9249e4960.

[Reporting paper](<https://www.sota2.com/research/paper/69b39a320636e5bf4afbcc8e.md>)

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

### Gemma3-it 27B

Proactive Inquiry: 34.2. Result ID: 69b3d87847f34ce9249e4966.

[Reporting paper](<https://www.sota2.com/research/paper/69b39a320636e5bf4afbcc8e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa779f1e209131cea746cd.md>)

Recorded evaluation configuration: {"Model size":"27B"}. This record does not assert independent reproduction.

### DeepSeek-V3.2 Thinking

Proactive Inquiry: 29.2. Result ID: 69b3d87847f34ce9249e4962.

[Reporting paper](<https://www.sota2.com/research/paper/69b39a320636e5bf4afbcc8e.md>)

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

### Llama3.1-70B-it

Proactive Inquiry: 22.4. Result ID: 69b3d87847f34ce9249e4964.

[Reporting paper](<https://www.sota2.com/research/paper/69b39a320636e5bf4afbcc8e.md>)

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

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

Recorded evaluation configuration: {"Model size":"70B"}. This record does not assert independent reproduction.

### DeepSeek-V3.2

Proactive Inquiry: 20.9. Result ID: 69b3d87847f34ce9249e4961.

[Reporting paper](<https://www.sota2.com/research/paper/69b39a320636e5bf4afbcc8e.md>)

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

### GPT-5

Proactive Inquiry: 16.6. Result ID: 69b3d87847f34ce9249e495e.

[Reporting paper](<https://www.sota2.com/research/paper/69b39a320636e5bf4afbcc8e.md>)

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

### GPT-4o

Proactive Inquiry: 16.5. Result ID: 69b3d87847f34ce9249e495f.

[Reporting paper](<https://www.sota2.com/research/paper/69b39a320636e5bf4afbcc8e.md>)

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

### Gemma3-it 12B

Proactive Inquiry: 13.7. Result ID: 69b3d87847f34ce9249e4965.

[Reporting paper](<https://www.sota2.com/research/paper/69b39a320636e5bf4afbcc8e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa779f1e209131cea746cd.md>)

Recorded evaluation configuration: {"Model size":"12B"}. This record does not assert independent reproduction.

### Llama3.1-8B-it

Proactive Inquiry: 12.6. Result ID: 69b3d87847f34ce9249e4963.

[Reporting paper](<https://www.sota2.com/research/paper/69b39a320636e5bf4afbcc8e.md>)

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

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

Recorded evaluation configuration: {"Model size":"8B"}. This record does not assert independent reproduction.

### Qwen3-it 32B

Proactive Inquiry: 9.8. Result ID: 69b3d87847f34ce9249e496b.

[Reporting paper](<https://www.sota2.com/research/paper/69b39a320636e5bf4afbcc8e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Model size":"32B"}. This record does not assert independent reproduction.

### Qwen3-it 8B

Proactive Inquiry: 5.1. Result ID: 69b3d87847f34ce9249e4969.

[Reporting paper](<https://www.sota2.com/research/paper/69b39a320636e5bf4afbcc8e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Model size":"8B"}. This record does not assert independent reproduction.

### Qwen3-it 14B

Proactive Inquiry: 4.9. Result ID: 69b3d87847f34ce9249e496a.

[Reporting paper](<https://www.sota2.com/research/paper/69b39a320636e5bf4afbcc8e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Model size":"14B"}. This record does not assert independent reproduction.

### GPT-oss-20B

Proactive Inquiry: 2. Result ID: 69b3d87847f34ce9249e4967.

[Reporting paper](<https://www.sota2.com/research/paper/69b39a320636e5bf4afbcc8e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ab01e209131cea84a0c.md>)

Recorded evaluation configuration: {"Model size":"20B"}. This record does not assert independent reproduction.

### GPT-oss-120B

Proactive Inquiry: 1.7. Result ID: 69b3d87847f34ce9249e4968.

[Reporting paper](<https://www.sota2.com/research/paper/69b39a320636e5bf4afbcc8e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ab01e209131cea84a0c.md>)

Recorded evaluation configuration: {"Model size":"120B"}. This record does not assert independent reproduction.

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