# Personality Alignment Evaluation on Big Five Inventory (BFI) and Behavioral Tasks

Source: [Personality Alignment Evaluation on Big Five Inventory (BFI) and Behavioral Tasks](<https://www.sota2.com/research/sota/personality-alignment-evaluation-on-big-five-inventory-bfi-and-behavioral-tasks>)

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

Data updated: 2026-05-29T10:13:35.647Z

Evaluation of model performance on personality alignment using the Big Five Inventory (BFI) and associated behavioral tasks, assessed using specific knowledge, difference, and delta metrics (KE, DE, ΔE, etc.).

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 | Personality Alignment Evaluation |
| Dataset (including any stated split) | Big Five Inventory (BFI) and Behavioral Tasks |
| Metric | Knowledge Score (E) |
| Unit | SCALAR |
| 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

- [Knowledge Score (E)](<https://www.sota2.com/research/sota/personality-alignment-evaluation-on-big-five-inventory-bfi-and-behavioral-tasks.md?metric=Knowledge%20Score%20(E)>): Higher is better; unit: SCALAR.

- [Difference Score (E)](<https://www.sota2.com/research/sota/personality-alignment-evaluation-on-big-five-inventory-bfi-and-behavioral-tasks.md?metric=Difference%20Score%20(E)>): Lower is better; unit: SCALAR.

- [Delta Score (E)](<https://www.sota2.com/research/sota/personality-alignment-evaluation-on-big-five-inventory-bfi-and-behavioral-tasks.md?metric=Delta%20Score%20(E)>): Lower is better; unit: SCALAR.

- [Knowledge Score (A)](<https://www.sota2.com/research/sota/personality-alignment-evaluation-on-big-five-inventory-bfi-and-behavioral-tasks.md?metric=Knowledge%20Score%20(A)>): Higher is better; unit: SCALAR.

- [Difference Score (A)](<https://www.sota2.com/research/sota/personality-alignment-evaluation-on-big-five-inventory-bfi-and-behavioral-tasks.md?metric=Difference%20Score%20(A)>): Lower is better; unit: SCALAR.

- [Delta Score (A)](<https://www.sota2.com/research/sota/personality-alignment-evaluation-on-big-five-inventory-bfi-and-behavioral-tasks.md?metric=Delta%20Score%20(A)>): Lower is better; unit: SCALAR.

- [Knowledge Score (C)](<https://www.sota2.com/research/sota/personality-alignment-evaluation-on-big-five-inventory-bfi-and-behavioral-tasks.md?metric=Knowledge%20Score%20(C)>): Higher is better; unit: SCALAR.

- [Difference Score (C)](<https://www.sota2.com/research/sota/personality-alignment-evaluation-on-big-five-inventory-bfi-and-behavioral-tasks.md?metric=Difference%20Score%20(C)>): Lower is better; unit: SCALAR.

- [Delta Score (C)](<https://www.sota2.com/research/sota/personality-alignment-evaluation-on-big-five-inventory-bfi-and-behavioral-tasks.md?metric=Delta%20Score%20(C)>): Lower is better; unit: SCALAR.

- [Knowledge Score (N)](<https://www.sota2.com/research/sota/personality-alignment-evaluation-on-big-five-inventory-bfi-and-behavioral-tasks.md?metric=Knowledge%20Score%20(N)>): Higher is better; unit: SCALAR.

- [Difference Score (N)](<https://www.sota2.com/research/sota/personality-alignment-evaluation-on-big-five-inventory-bfi-and-behavioral-tasks.md?metric=Difference%20Score%20(N)>): Lower is better; unit: SCALAR.

- [Delta Score (N)](<https://www.sota2.com/research/sota/personality-alignment-evaluation-on-big-five-inventory-bfi-and-behavioral-tasks.md?metric=Delta%20Score%20(N)>): Lower is better; unit: SCALAR.

- [Knowledge Score (O)](<https://www.sota2.com/research/sota/personality-alignment-evaluation-on-big-five-inventory-bfi-and-behavioral-tasks.md?metric=Knowledge%20Score%20(O)>): Higher is better; unit: SCALAR.

- [Difference Score (O)](<https://www.sota2.com/research/sota/personality-alignment-evaluation-on-big-five-inventory-bfi-and-behavioral-tasks.md?metric=Difference%20Score%20(O)>): Lower is better; unit: SCALAR.

- [Delta Score (O)](<https://www.sota2.com/research/sota/personality-alignment-evaluation-on-big-five-inventory-bfi-and-behavioral-tasks.md?metric=Delta%20Score%20(O)>): Lower is better; unit: SCALAR.

- [General Knowledge Difference (GKD)](<https://www.sota2.com/research/sota/personality-alignment-evaluation-on-big-five-inventory-bfi-and-behavioral-tasks.md?metric=General%20Knowledge%20Difference%20(GKD)>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Knowledge Score (E) | Result date | Report paper |
| --- | --- | --- | --- |
| deepseek-v3.1 | 3.61 | Not recorded | 6a191dd4dbd7150506f82ad7 |
| qwen3-8b | 3.58 | Not recorded | 6a191dd4dbd7150506f82ad7 |
| claude-sonnet-4-6 | 3.58 | Not recorded | 6a191dd4dbd7150506f82ad7 |
| deepseek-v3.2 | 3.56 | Not recorded | 6a191dd4dbd7150506f82ad7 |
| qwen3-32b | 3.56 | Not recorded | 6a191dd4dbd7150506f82ad7 |
| glm-5 | 3.56 | Not recorded | 6a191dd4dbd7150506f82ad7 |
| gemini-3.1-pro | 3.42 | Not recorded | 6a191dd4dbd7150506f82ad7 |
| minimax-m2.5 | 3.33 | Not recorded | 6a191dd4dbd7150506f82ad7 |
| gpt-4o | 3.19 | Not recorded | 6a191dd4dbd7150506f82ad7 |
| qwen3-235b-thinking | 3.14 | Not recorded | 6a191dd4dbd7150506f82ad7 |
| deepseek-v3 | 3.11 | Not recorded | 6a191dd4dbd7150506f82ad7 |
| deepseek-v4-flash | 3.11 | Not recorded | 6a191dd4dbd7150506f82ad7 |
| deepseek-v4-pro | 3.09 | Not recorded | 6a191dd4dbd7150506f82ad7 |
| qwen3-1.7b | 3.08 | Not recorded | 6a191dd4dbd7150506f82ad7 |
| Human Baseline | 2.86 | Not recorded | 6a191dd4dbd7150506f82ad7 |

### deepseek-v3.1

Knowledge Score (E): 3.61. Result ID: 6a1965ccfbc373592c144801.

[Reporting paper](<https://www.sota2.com/research/paper/6a191dd4dbd7150506f82ad7.md>)

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

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

### qwen3-8b

Knowledge Score (E): 3.58. Result ID: 6a1965ccfbc373592c144806.

[Reporting paper](<https://www.sota2.com/research/paper/6a191dd4dbd7150506f82ad7.md>)

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

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

### claude-sonnet-4-6

Knowledge Score (E): 3.58. Result ID: 6a1965ccfbc373592c144809.

[Reporting paper](<https://www.sota2.com/research/paper/6a191dd4dbd7150506f82ad7.md>)

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

### deepseek-v3.2

Knowledge Score (E): 3.56. Result ID: 6a1965ccfbc373592c144802.

[Reporting paper](<https://www.sota2.com/research/paper/6a191dd4dbd7150506f82ad7.md>)

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

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

### qwen3-32b

Knowledge Score (E): 3.56. Result ID: 6a1965ccfbc373592c144807.

[Reporting paper](<https://www.sota2.com/research/paper/6a191dd4dbd7150506f82ad7.md>)

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

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

### glm-5

Knowledge Score (E): 3.56. Result ID: 6a1965ccfbc373592c14480b.

[Reporting paper](<https://www.sota2.com/research/paper/6a191dd4dbd7150506f82ad7.md>)

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

### gemini-3.1-pro

Knowledge Score (E): 3.42. Result ID: 6a1965ccfbc373592c14480a.

[Reporting paper](<https://www.sota2.com/research/paper/6a191dd4dbd7150506f82ad7.md>)

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

### minimax-m2.5

Knowledge Score (E): 3.33. Result ID: 6a1965ccfbc373592c14480d.

[Reporting paper](<https://www.sota2.com/research/paper/6a191dd4dbd7150506f82ad7.md>)

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

### gpt-4o

Knowledge Score (E): 3.19. Result ID: 6a1965ccfbc373592c14480c.

[Reporting paper](<https://www.sota2.com/research/paper/6a191dd4dbd7150506f82ad7.md>)

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

### qwen3-235b-thinking

Knowledge Score (E): 3.14. Result ID: 6a1965ccfbc373592c144808.

[Reporting paper](<https://www.sota2.com/research/paper/6a191dd4dbd7150506f82ad7.md>)

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

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

### deepseek-v3

Knowledge Score (E): 3.11. Result ID: 6a1965ccfbc373592c144800.

[Reporting paper](<https://www.sota2.com/research/paper/6a191dd4dbd7150506f82ad7.md>)

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

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

### deepseek-v4-flash

Knowledge Score (E): 3.11. Result ID: 6a1965ccfbc373592c144803.

[Reporting paper](<https://www.sota2.com/research/paper/6a191dd4dbd7150506f82ad7.md>)

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

### deepseek-v4-pro

Knowledge Score (E): 3.09. Result ID: 6a1965ccfbc373592c144804.

[Reporting paper](<https://www.sota2.com/research/paper/6a191dd4dbd7150506f82ad7.md>)

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

### qwen3-1.7b

Knowledge Score (E): 3.08. Result ID: 6a1965ccfbc373592c144805.

[Reporting paper](<https://www.sota2.com/research/paper/6a191dd4dbd7150506f82ad7.md>)

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

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

### Human Baseline

Knowledge Score (E): 2.86. Result ID: 6a1965ccfbc373592c1447ff.

[Reporting paper](<https://www.sota2.com/research/paper/6a191dd4dbd7150506f82ad7.md>)

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

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