# Personalized Assistant Interaction on LifeSim-Eval Single-Scenario

Source: [Personalized Assistant Interaction on LifeSim-Eval Single-Scenario](<https://www.sota2.com/research/sota/personalized-assistant-interaction-on-lifesim-eval-single-scenario>)

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

Data updated: 2026-03-13T09:27:39.587Z

Evaluation of personalized assistant interaction capabilities using the LifeSim-Eval Single-Scenario dataset, measuring metrics such as Intent Recognition, Coherence, and Persona Alignment.

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 | Personalized Assistant Interaction |
| Dataset (including any stated split) | LifeSim-Eval Single-Scenario |
| Metric | Explicit Intent Recognition |
| 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

- [Explicit Intent Recognition](<https://www.sota2.com/research/sota/personalized-assistant-interaction-on-lifesim-eval-single-scenario.md?metric=Explicit%20Intent%20Recognition>): Higher is better; unit: PERCENT.

- [Implicit Intent Recognition](<https://www.sota2.com/research/sota/personalized-assistant-interaction-on-lifesim-eval-single-scenario.md?metric=Implicit%20Intent%20Recognition>): Higher is better; unit: PERCENT.

- [Explicit Intent Completion](<https://www.sota2.com/research/sota/personalized-assistant-interaction-on-lifesim-eval-single-scenario.md?metric=Explicit%20Intent%20Completion>): Higher is better; unit: PERCENT.

- [Implicit Intent Completion](<https://www.sota2.com/research/sota/personalized-assistant-interaction-on-lifesim-eval-single-scenario.md?metric=Implicit%20Intent%20Completion>): Higher is better; unit: PERCENT.

- [Naturalness](<https://www.sota2.com/research/sota/personalized-assistant-interaction-on-lifesim-eval-single-scenario.md?metric=Naturalness>): Higher is better; unit: SCALAR.

- [Coherence](<https://www.sota2.com/research/sota/personalized-assistant-interaction-on-lifesim-eval-single-scenario.md?metric=Coherence>): Higher is better; unit: SCALAR.

- [Profile Recovery](<https://www.sota2.com/research/sota/personalized-assistant-interaction-on-lifesim-eval-single-scenario.md?metric=Profile%20Recovery>): Higher is better; unit: PERCENT.

- [Persona Alignment](<https://www.sota2.com/research/sota/personalized-assistant-interaction-on-lifesim-eval-single-scenario.md?metric=Persona%20Alignment>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Explicit Intent Recognition | Result date | Report paper |
| --- | --- | --- | --- |
| DeepSeek-V3.2 Thinking | 80.6 | Not recorded | 69b39a320636e5bf4afbcc8e |
| GPT-5 | 79.5 | Not recorded | 69b39a320636e5bf4afbcc8e |
| GPT-4o | 79 | Not recorded | 69b39a320636e5bf4afbcc8e |
| DeepSeek-V3.2 | 78.6 | Not recorded | 69b39a320636e5bf4afbcc8e |
| Qwen3 14B | 77 | Not recorded | 69b39a320636e5bf4afbcc8e |
| gpt-oss 20B | 76.9 | Not recorded | 69b39a320636e5bf4afbcc8e |
| Qwen3 32B | 76.6 | Not recorded | 69b39a320636e5bf4afbcc8e |
| gpt-oss 120B | 76.4 | Not recorded | 69b39a320636e5bf4afbcc8e |
| Claude-Sonnet-4.5 | 76.1 | Not recorded | 69b39a320636e5bf4afbcc8e |
| Qwen3 8B | 75.7 | Not recorded | 69b39a320636e5bf4afbcc8e |
| Gemma3-it 27B | 72.7 | Not recorded | 69b39a320636e5bf4afbcc8e |
| Llama3.1-it 70B | 71.7 | Not recorded | 69b39a320636e5bf4afbcc8e |
| Llama3.1-it 8B | 70.3 | Not recorded | 69b39a320636e5bf4afbcc8e |
| Gemma3-it 12B | 67.8 | Not recorded | 69b39a320636e5bf4afbcc8e |

### DeepSeek-V3.2 Thinking

Explicit Intent Recognition: 80.6. Result ID: 69b3d87847f34ce9249e4954.

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

Recorded evaluation configuration: {"Access Type":"Open-source"}. This record does not assert independent reproduction.

### GPT-5

Explicit Intent Recognition: 79.5. Result ID: 69b3d87847f34ce9249e4950.

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

Recorded evaluation configuration: {"Access Type":"Close-source"}. This record does not assert independent reproduction.

### GPT-4o

Explicit Intent Recognition: 79. Result ID: 69b3d87847f34ce9249e4951.

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

Recorded evaluation configuration: {"Access Type":"Close-source"}. This record does not assert independent reproduction.

### DeepSeek-V3.2

Explicit Intent Recognition: 78.6. Result ID: 69b3d87847f34ce9249e4953.

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

Recorded evaluation configuration: {"Access Type":"Open-source"}. This record does not assert independent reproduction.

### Qwen3 14B

Explicit Intent Recognition: 77. Result ID: 69b3d87847f34ce9249e495c.

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

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

Recorded evaluation configuration: {"Access Type":"Open-source"}. This record does not assert independent reproduction.

### gpt-oss 20B

Explicit Intent Recognition: 76.9. Result ID: 69b3d87847f34ce9249e4959.

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

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

Recorded evaluation configuration: {"Access Type":"Open-source"}. This record does not assert independent reproduction.

### Qwen3 32B

Explicit Intent Recognition: 76.6. Result ID: 69b3d87847f34ce9249e495d.

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

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

Recorded evaluation configuration: {"Access Type":"Open-source"}. This record does not assert independent reproduction.

### gpt-oss 120B

Explicit Intent Recognition: 76.4. Result ID: 69b3d87847f34ce9249e495a.

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

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

Recorded evaluation configuration: {"Access Type":"Open-source"}. This record does not assert independent reproduction.

### Claude-Sonnet-4.5

Explicit Intent Recognition: 76.1. Result ID: 69b3d87847f34ce9249e4952.

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

Recorded evaluation configuration: {"Access Type":"Close-source"}. This record does not assert independent reproduction.

### Qwen3 8B

Explicit Intent Recognition: 75.7. Result ID: 69b3d87847f34ce9249e495b.

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

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

Recorded evaluation configuration: {"Access Type":"Open-source"}. This record does not assert independent reproduction.

### Gemma3-it 27B

Explicit Intent Recognition: 72.7. Result ID: 69b3d87847f34ce9249e4958.

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

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

Recorded evaluation configuration: {"Access Type":"Open-source"}. This record does not assert independent reproduction.

### Llama3.1-it 70B

Explicit Intent Recognition: 71.7. Result ID: 69b3d87847f34ce9249e4956.

[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: {"Access Type":"Open-source"}. This record does not assert independent reproduction.

### Llama3.1-it 8B

Explicit Intent Recognition: 70.3. Result ID: 69b3d87847f34ce9249e4955.

[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: {"Access Type":"Open-source"}. This record does not assert independent reproduction.

### Gemma3-it 12B

Explicit Intent Recognition: 67.8. Result ID: 69b3d87847f34ce9249e4957.

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

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

Recorded evaluation configuration: {"Access Type":"Open-source"}. This record does not assert independent reproduction.

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