# Contradiction Intensity Agreement on RevCI (test)

Source: [Contradiction Intensity Agreement on RevCI (test)](<https://www.sota2.com/research/sota/contradiction-intensity-agreement-on-revci-test>)

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

Data updated: 2026-05-12T14:52:40.880Z

Evaluation of model performance on the test split of the RevCI dataset, focusing on Contradiction Intensity Agreement, measured using Kappa (κ), Rho (ρ), and Tau (τ).

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 | Contradiction Intensity Agreement |
| Dataset (including any stated split) | RevCI (test) |
| Metric | Kappa (κ) |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 13 of 13 |
| 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

- [Kappa (κ)](<https://www.sota2.com/research/sota/contradiction-intensity-agreement-on-revci-test.md?metric=Kappa%20(%CE%BA)>): Higher is better; unit: SCALAR.

- [Rho (ρ)](<https://www.sota2.com/research/sota/contradiction-intensity-agreement-on-revci-test.md?metric=Rho%20(%CF%81)>): Higher is better; unit: SCALAR.

- [Tau (τ)](<https://www.sota2.com/research/sota/contradiction-intensity-agreement-on-revci-test.md?metric=Tau%20(%CF%84)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Kappa (κ) | Result date | Report paper |
| --- | --- | --- | --- |
| IMPACT-P | 0.3862 | Not recorded | 6a02b49adbc836b87d824df8 |
| IMPACT-OA | 0.327 | Not recorded | 6a02b49adbc836b87d824df8 |
| Gemini-3 Flash | 0.3041 | Not recorded | 6a02b49adbc836b87d824df8 |
| CourtEval | 0.286 | Not recorded | 6a02b49adbc836b87d824df8 |
| ChatEval | 0.281 | Not recorded | 6a02b49adbc836b87d824df8 |
| MAD | 0.272 | Not recorded | 6a02b49adbc836b87d824df8 |
| Self-Refine | 0.268 | Not recorded | 6a02b49adbc836b87d824df8 |
| GPT-5.2 | 0.2612 | Not recorded | 6a02b49adbc836b87d824df8 |
| Debate | 0.255 | Not recorded | 6a02b49adbc836b87d824df8 |
| LLaMA-3-8B-Instruct | 0.2488 | Not recorded | 6a02b49adbc836b87d824df8 |
| LLaMA-4 Maverick | 0.2348 | Not recorded | 6a02b49adbc836b87d824df8 |
| TIDE | 0.2202 | Not recorded | 6a02b49adbc836b87d824df8 |
| Qwen-2.5-7B-Instruct | 0.1859 | Not recorded | 6a02b49adbc836b87d824df8 |

### IMPACT-P

Kappa (κ): 0.3862. Result ID: 6a033e3c47f34ce924e82e4b.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b49adbc836b87d824df8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b49adbc836b87d824df8.md>)

Recorded evaluation configuration: {"Category":"Our Proposed"}. This record does not assert independent reproduction.

### IMPACT-OA

Kappa (κ): 0.327. Result ID: 6a033e3c47f34ce924e82e4a.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b49adbc836b87d824df8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b49adbc836b87d824df8.md>)

Recorded evaluation configuration: {"Category":"Our Proposed"}. This record does not assert independent reproduction.

### Gemini-3 Flash

Kappa (κ): 0.3041. Result ID: 6a033e3c47f34ce924e82e42.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b49adbc836b87d824df8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78731e209131cea78622.md>)

Recorded evaluation configuration: {"Category":"Single-agent (CoT)"}. This record does not assert independent reproduction.

### CourtEval

Kappa (κ): 0.286. Result ID: 6a033e3c47f34ce924e82e49.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b49adbc836b87d824df8.md>)

Recorded evaluation configuration: {"Category":"Generic multi-agent"}. This record does not assert independent reproduction.

### ChatEval

Kappa (κ): 0.281. Result ID: 6a033e3c47f34ce924e82e48.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b49adbc836b87d824df8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa705a1e209131cea4a819.md>)

Recorded evaluation configuration: {"Category":"Generic multi-agent"}. This record does not assert independent reproduction.

### MAD

Kappa (κ): 0.272. Result ID: 6a033e3c47f34ce924e82e47.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b49adbc836b87d824df8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75171e209131cea65abb.md>)

Recorded evaluation configuration: {"Category":"Generic multi-agent"}. This record does not assert independent reproduction.

### Self-Refine

Kappa (κ): 0.268. Result ID: 6a033e3c47f34ce924e82e45.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b49adbc836b87d824df8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fc4.md>)

Recorded evaluation configuration: {"Category":"Generic multi-agent"}. This record does not assert independent reproduction.

### GPT-5.2

Kappa (κ): 0.2612. Result ID: 6a033e3c47f34ce924e82e40.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b49adbc836b87d824df8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa727a1e209131cea56a1e.md>)

[Implementation](<https://github.com/openai/evals>)

Recorded evaluation configuration: {"Category":"Single-agent (CoT)"}. This record does not assert independent reproduction.

### Debate

Kappa (κ): 0.255. Result ID: 6a033e3c47f34ce924e82e46.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b49adbc836b87d824df8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73501e209131cea5bc34.md>)

Recorded evaluation configuration: {"Category":"Generic multi-agent"}. This record does not assert independent reproduction.

### LLaMA-3-8B-Instruct

Kappa (κ): 0.2488. Result ID: 6a033e3c47f34ce924e82e43.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b49adbc836b87d824df8.md>)

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

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

Recorded evaluation configuration: {"Category":"Single-agent (CoT)"}. This record does not assert independent reproduction.

### LLaMA-4 Maverick

Kappa (κ): 0.2348. Result ID: 6a033e3c47f34ce924e82e41.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b49adbc836b87d824df8.md>)

Recorded evaluation configuration: {"Category":"Single-agent (CoT)"}. This record does not assert independent reproduction.

### TIDE

Kappa (κ): 0.2202. Result ID: 6a033e3c47f34ce924e82e4c.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b49adbc836b87d824df8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b49adbc836b87d824df8.md>)

Recorded evaluation configuration: {"Category":"Our Proposed"}. This record does not assert independent reproduction.

### Qwen-2.5-7B-Instruct

Kappa (κ): 0.1859. Result ID: 6a033e3c47f34ce924e82e44.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b49adbc836b87d824df8.md>)

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

Recorded evaluation configuration: {"Category":"Single-agent (CoT)"}. This record does not assert independent reproduction.

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