# Three-way probability ranking on COMMON2SENSE paired

Source: [Three-way probability ranking on COMMON2SENSE paired](<https://www.sota2.com/research/sota/three-way-probability-ranking-on-common2sense-paired>)

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

Data updated: 2026-04-15T09:22:41.398Z

Evaluation of model performance on the COMMON2SENSE paired dataset using Three-way probability ranking, measured by F1 scores for categories C1, C2, Equality, and Macro F1.

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 | Three-way probability ranking |
| Dataset (including any stated split) | COMMON2SENSE paired |
| Metric | F1 (C1) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 30 of 30 |
| 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

- [F1 (C1)](<https://www.sota2.com/research/sota/three-way-probability-ranking-on-common2sense-paired.md?metric=F1%20(C1)>): Higher is better; unit: PERCENT.

- [F1 (C2)](<https://www.sota2.com/research/sota/three-way-probability-ranking-on-common2sense-paired.md?metric=F1%20(C2)>): Higher is better; unit: PERCENT.

- [F1 (Equality)](<https://www.sota2.com/research/sota/three-way-probability-ranking-on-common2sense-paired.md?metric=F1%20(Equality)>): Higher is better; unit: PERCENT.

- [Macro F1](<https://www.sota2.com/research/sota/three-way-probability-ranking-on-common2sense-paired.md?metric=Macro%20F1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | F1 (C1) | Result date | Report paper |
| --- | --- | --- | --- |
| IDEA | 76.2 | Not recorded | 69df1bb57d0172140ec7ba5e |
| IDEA w/o MC | 73.2 | Not recorded | 69df1bb57d0172140ec7ba5e |
| IDEA | 72.8 | Not recorded | 69df1bb57d0172140ec7ba5e |
| IDEA w/o Inter | 71.5 | Not recorded | 69df1bb57d0172140ec7ba5e |
| IDEA w/o EM | 70.6 | Not recorded | 69df1bb57d0172140ec7ba5e |
| IDEA w/o MC | 68.3 | Not recorded | 69df1bb57d0172140ec7ba5e |
| IDEA w/o Inter | 67.5 | Not recorded | 69df1bb57d0172140ec7ba5e |
| IDEA w/o EM | 65.8 | Not recorded | 69df1bb57d0172140ec7ba5e |
| PWC | 61.5 | Not recorded | 69df1bb57d0172140ec7ba5e |
| BIRD | 59 | Not recorded | 69df1bb57d0172140ec7ba5e |
| IDEA | 57.5 | Not recorded | 69df1bb57d0172140ec7ba5e |
| BIRD | 55.2 | Not recorded | 69df1bb57d0172140ec7ba5e |
| PWC | 54.8 | Not recorded | 69df1bb57d0172140ec7ba5e |
| PWC | 54.2 | Not recorded | 69df1bb57d0172140ec7ba5e |
| IDEA w/o MC | 53.6 | Not recorded | 69df1bb57d0172140ec7ba5e |
| IDEA w/o Inter | 52.2 | Not recorded | 69df1bb57d0172140ec7ba5e |
| IDEA w/o EM | 50.5 | Not recorded | 69df1bb57d0172140ec7ba5e |
| CoT | 45.5 | Not recorded | 69df1bb57d0172140ec7ba5e |
| Vanilla | 43.8 | Not recorded | 69df1bb57d0172140ec7ba5e |
| Vanilla | 41.8 | Not recorded | 69df1bb57d0172140ec7ba5e |
| BIRD | 39.8 | Not recorded | 69df1bb57d0172140ec7ba5e |
| Vanilla | 39.2 | Not recorded | 69df1bb57d0172140ec7ba5e |
| CoT | 38.2 | Not recorded | 69df1bb57d0172140ec7ba5e |
| CoT | 36.5 | Not recorded | 69df1bb57d0172140ec7ba5e |
| CoT | 35.2 | Not recorded | 69df1bb57d0172140ec7ba5e |
| Logit | 34.5 | Not recorded | 69df1bb57d0172140ec7ba5e |
| Random | 33.3 | Not recorded | 69df1bb57d0172140ec7ba5e |
| Logit | 32.2 | Not recorded | 69df1bb57d0172140ec7ba5e |
| CoT | 31.8 | Not recorded | 69df1bb57d0172140ec7ba5e |
| Logit | 28.1 | Not recorded | 69df1bb57d0172140ec7ba5e |

### IDEA

F1 (C1): 76.2. Result ID: 69df580947f34ce924c85bff.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

Recorded evaluation configuration: {"Model":"Qwen-3-32B"}. This record does not assert independent reproduction.

### IDEA w/o MC

F1 (C1): 73.2. Result ID: 69df580947f34ce924c85bfe.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

Recorded evaluation configuration: {"Model":"Qwen-3-32B"}. This record does not assert independent reproduction.

### IDEA

F1 (C1): 72.8. Result ID: 69df580947f34ce924c85bf6.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

Recorded evaluation configuration: {"Model":"Qwen-3-8B"}. This record does not assert independent reproduction.

### IDEA w/o Inter

F1 (C1): 71.5. Result ID: 69df580947f34ce924c85bfc.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

Recorded evaluation configuration: {"Model":"Qwen-3-32B"}. This record does not assert independent reproduction.

### IDEA w/o EM

F1 (C1): 70.6. Result ID: 69df580947f34ce924c85bfd.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

Recorded evaluation configuration: {"Model":"Qwen-3-32B"}. This record does not assert independent reproduction.

### IDEA w/o MC

F1 (C1): 68.3. Result ID: 69df580947f34ce924c85bf5.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

Recorded evaluation configuration: {"Model":"Qwen-3-8B"}. This record does not assert independent reproduction.

### IDEA w/o Inter

F1 (C1): 67.5. Result ID: 69df580947f34ce924c85bf3.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

Recorded evaluation configuration: {"Model":"Qwen-3-8B"}. This record does not assert independent reproduction.

### IDEA w/o EM

F1 (C1): 65.8. Result ID: 69df580947f34ce924c85bf4.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

Recorded evaluation configuration: {"Model":"Qwen-3-8B"}. This record does not assert independent reproduction.

### PWC

F1 (C1): 61.5. Result ID: 69df580947f34ce924c85bf2.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

Recorded evaluation configuration: {"Model":"Qwen-3-8B"}. This record does not assert independent reproduction.

### BIRD

F1 (C1): 59. Result ID: 69df580947f34ce924c85bfa.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c5e1e209131cea8dc7d.md>)

Recorded evaluation configuration: {"Model":"Qwen-3-32B"}. This record does not assert independent reproduction.

### IDEA

F1 (C1): 57.5. Result ID: 69df580947f34ce924c85bed.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

Recorded evaluation configuration: {"Model":"Qwen-3-4B"}. This record does not assert independent reproduction.

### BIRD

F1 (C1): 55.2. Result ID: 69df580947f34ce924c85bf1.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c5e1e209131cea8dc7d.md>)

Recorded evaluation configuration: {"Model":"Qwen-3-8B"}. This record does not assert independent reproduction.

### PWC

F1 (C1): 54.8. Result ID: 69df580947f34ce924c85bfb.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

Recorded evaluation configuration: {"Model":"Qwen-3-32B"}. This record does not assert independent reproduction.

### PWC

F1 (C1): 54.2. Result ID: 69df580947f34ce924c85be9.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

Recorded evaluation configuration: {"Model":"Qwen-3-4B"}. This record does not assert independent reproduction.

### IDEA w/o MC

F1 (C1): 53.6. Result ID: 69df580947f34ce924c85bec.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

Recorded evaluation configuration: {"Model":"Qwen-3-4B"}. This record does not assert independent reproduction.

### IDEA w/o Inter

F1 (C1): 52.2. Result ID: 69df580947f34ce924c85bea.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

Recorded evaluation configuration: {"Model":"Qwen-3-4B"}. This record does not assert independent reproduction.

### IDEA w/o EM

F1 (C1): 50.5. Result ID: 69df580947f34ce924c85beb.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

Recorded evaluation configuration: {"Model":"Qwen-3-4B"}. This record does not assert independent reproduction.

### CoT

F1 (C1): 45.5. Result ID: 69df580947f34ce924c85be4.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

Recorded evaluation configuration: {"Model":"GPT-5.2"}. This record does not assert independent reproduction.

### Vanilla

F1 (C1): 43.8. Result ID: 69df580947f34ce924c85bf9.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eb61e209131cea41b33.md>)

Recorded evaluation configuration: {"Model":"Qwen-3-32B"}. This record does not assert independent reproduction.

### Vanilla

F1 (C1): 41.8. Result ID: 69df580947f34ce924c85bf0.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eb61e209131cea41b33.md>)

Recorded evaluation configuration: {"Model":"Qwen-3-8B"}. This record does not assert independent reproduction.

### BIRD

F1 (C1): 39.8. Result ID: 69df580947f34ce924c85be8.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c5e1e209131cea8dc7d.md>)

Recorded evaluation configuration: {"Model":"Qwen-3-4B"}. This record does not assert independent reproduction.

### Vanilla

F1 (C1): 39.2. Result ID: 69df580947f34ce924c85be7.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eb61e209131cea41b33.md>)

Recorded evaluation configuration: {"Model":"Qwen-3-4B"}. This record does not assert independent reproduction.

### CoT

F1 (C1): 38.2. Result ID: 69df580947f34ce924c85bf7.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

Recorded evaluation configuration: {"Model":"Qwen-3-32B"}. This record does not assert independent reproduction.

### CoT

F1 (C1): 36.5. Result ID: 69df580947f34ce924c85bee.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

Recorded evaluation configuration: {"Model":"Qwen-3-8B"}. This record does not assert independent reproduction.

### CoT

F1 (C1): 35.2. Result ID: 69df580947f34ce924c85be5.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

Recorded evaluation configuration: {"Model":"Qwen-3-4B"}. This record does not assert independent reproduction.

### Logit

F1 (C1): 34.5. Result ID: 69df580947f34ce924c85bf8.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6df71e209131cea3d034.md>)

Recorded evaluation configuration: {"Model":"Qwen-3-32B"}. This record does not assert independent reproduction.

### Random

F1 (C1): 33.3. Result ID: 69df580947f34ce924c85be2.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

Recorded evaluation configuration: {"Model":"N/A"}. This record does not assert independent reproduction.

### Logit

F1 (C1): 32.2. Result ID: 69df580947f34ce924c85bef.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6df71e209131cea3d034.md>)

Recorded evaluation configuration: {"Model":"Qwen-3-8B"}. This record does not assert independent reproduction.

### CoT

F1 (C1): 31.8. Result ID: 69df580947f34ce924c85be3.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

Recorded evaluation configuration: {"Model":"DeepSeek R1"}. This record does not assert independent reproduction.

### Logit

F1 (C1): 28.1. Result ID: 69df580947f34ce924c85be6.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6df71e209131cea3d034.md>)

Recorded evaluation configuration: {"Model":"Qwen-3-4B"}. This record does not assert independent reproduction.

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