# Claim Verification on ExClaim

Source: [Claim Verification on ExClaim](<https://www.sota2.com/research/sota/claim-verification-on-exclaim>)

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

Data updated: 2026-04-16T07:53:32.167Z

Evaluation of model performance on the ExClaim dataset for Claim Verification, reporting P, R, F1, RL, BS, and ES scores.

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 | Claim Verification |
| Dataset (including any stated split) | ExClaim |
| Metric | Precision (P) |
| 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

- [Precision (P)](<https://www.sota2.com/research/sota/claim-verification-on-exclaim.md?metric=Precision%20(P)>): Higher is better; unit: PERCENT.

- [Recall (R)](<https://www.sota2.com/research/sota/claim-verification-on-exclaim.md?metric=Recall%20(R)>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/claim-verification-on-exclaim.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [RL Score](<https://www.sota2.com/research/sota/claim-verification-on-exclaim.md?metric=RL%20Score>): Higher is better; unit: PERCENT.

- [BS Score](<https://www.sota2.com/research/sota/claim-verification-on-exclaim.md?metric=BS%20Score>): Higher is better; unit: PERCENT.

- [ES Score](<https://www.sota2.com/research/sota/claim-verification-on-exclaim.md?metric=ES%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Precision (P) | Result date | Report paper |
| --- | --- | --- | --- |
| CO-FACTCHECKER | 34 | Not recorded | 69e06cfc7d0172140ec7c987 |
| Verifier - MCTS | 31 | Not recorded | 69e06cfc7d0172140ec7c987 |
| Multi-Turn Dialogue | 31 | Not recorded | 69e06cfc7d0172140ec7c987 |
| CO-FACTCHECKER - w/o reward model | 31 | Not recorded | 69e06cfc7d0172140ec7c987 |
| CO-FACTCHECKER - w/o guidance tokens | 31 | Not recorded | 69e06cfc7d0172140ec7c987 |
| Verifier - best-of-N | 30 | Not recorded | 69e06cfc7d0172140ec7c987 |
| CO-FACTCHECKER - w/o remove / modify | 30 | Not recorded | 69e06cfc7d0172140ec7c987 |
| Verifier | 29 | Not recorded | 69e06cfc7d0172140ec7c987 |
| Verifier - self-refine | 29 | Not recorded | 69e06cfc7d0172140ec7c987 |
| Choose One | 29 | Not recorded | 69e06cfc7d0172140ec7c987 |
| SAFE | 26 | Not recorded | 69e06cfc7d0172140ec7c987 |
| FIRE | 24 | Not recorded | 69e06cfc7d0172140ec7c987 |
| Deep Research | 22 | Not recorded | 69e06cfc7d0172140ec7c987 |
| FactCheckGPT | 21 | Not recorded | 69e06cfc7d0172140ec7c987 |

### CO-FACTCHECKER

Precision (P): 34. Result ID: 69e0955e47f34ce924c99f24.

[Reporting paper](<https://www.sota2.com/research/paper/69e06cfc7d0172140ec7c987.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e06cfc7d0172140ec7c987.md>)

Recorded evaluation configuration: {"System Category":"Simulated Human-AI Collaboration","Oracle Simulation":"Using an Oracle"}. This record does not assert independent reproduction.

### Verifier - MCTS

Precision (P): 31. Result ID: 69e0955e47f34ce924c99f20.

[Reporting paper](<https://www.sota2.com/research/paper/69e06cfc7d0172140ec7c987.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75c11e209131cea69c00.md>)

Recorded evaluation configuration: {"System Category":"Autonomous","Search/Refinement Strategy":"MCTS"}. This record does not assert independent reproduction.

### Multi-Turn Dialogue

Precision (P): 31. Result ID: 69e0955e47f34ce924c99f23.

[Reporting paper](<https://www.sota2.com/research/paper/69e06cfc7d0172140ec7c987.md>)

Recorded evaluation configuration: {"System Category":"Simulated Human-AI Collaboration","Oracle Simulation":"Using an Oracle"}. This record does not assert independent reproduction.

### CO-FACTCHECKER - w/o reward model

Precision (P): 31. Result ID: 69e0955e47f34ce924c99f25.

[Reporting paper](<https://www.sota2.com/research/paper/69e06cfc7d0172140ec7c987.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e06cfc7d0172140ec7c987.md>)

Recorded evaluation configuration: {"System Category":"Simulated Human-AI Collaboration","Oracle Simulation":"Using an Oracle","Ablation Setting":"w/o reward model"}. This record does not assert independent reproduction.

### CO-FACTCHECKER - w/o guidance tokens

Precision (P): 31. Result ID: 69e0955e47f34ce924c99f27.

[Reporting paper](<https://www.sota2.com/research/paper/69e06cfc7d0172140ec7c987.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e06cfc7d0172140ec7c987.md>)

Recorded evaluation configuration: {"System Category":"Simulated Human-AI Collaboration","Oracle Simulation":"Using an Oracle","Ablation Setting":"w/o guidance tokens"}. This record does not assert independent reproduction.

### Verifier - best-of-N

Precision (P): 30. Result ID: 69e0955e47f34ce924c99f1e.

[Reporting paper](<https://www.sota2.com/research/paper/69e06cfc7d0172140ec7c987.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bd91e209131cea3091a.md>)

Recorded evaluation configuration: {"System Category":"Autonomous","Search/Refinement Strategy":"best-of-N"}. This record does not assert independent reproduction.

### CO-FACTCHECKER - w/o remove / modify

Precision (P): 30. Result ID: 69e0955e47f34ce924c99f26.

[Reporting paper](<https://www.sota2.com/research/paper/69e06cfc7d0172140ec7c987.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e06cfc7d0172140ec7c987.md>)

Recorded evaluation configuration: {"System Category":"Simulated Human-AI Collaboration","Oracle Simulation":"Using an Oracle","Ablation Setting":"w/o remove / modify"}. This record does not assert independent reproduction.

### Verifier

Precision (P): 29. Result ID: 69e0955e47f34ce924c99f1d.

[Reporting paper](<https://www.sota2.com/research/paper/69e06cfc7d0172140ec7c987.md>)

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

### Verifier - self-refine

Precision (P): 29. Result ID: 69e0955e47f34ce924c99f1f.

[Reporting paper](<https://www.sota2.com/research/paper/69e06cfc7d0172140ec7c987.md>)

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

Recorded evaluation configuration: {"System Category":"Autonomous","Search/Refinement Strategy":"self-refine"}. This record does not assert independent reproduction.

### Choose One

Precision (P): 29. Result ID: 69e0955e47f34ce924c99f22.

[Reporting paper](<https://www.sota2.com/research/paper/69e06cfc7d0172140ec7c987.md>)

Recorded evaluation configuration: {"System Category":"Simulated Human-AI Collaboration","Oracle Simulation":"Using an Oracle"}. This record does not assert independent reproduction.

### SAFE

Precision (P): 26. Result ID: 69e0955e47f34ce924c99f1c.

[Reporting paper](<https://www.sota2.com/research/paper/69e06cfc7d0172140ec7c987.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa759c1e209131cea68f16.md>)

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

### FIRE

Precision (P): 24. Result ID: 69e0955e47f34ce924c99f1b.

[Reporting paper](<https://www.sota2.com/research/paper/69e06cfc7d0172140ec7c987.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c471e209131cea8d5e1.md>)

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

### Deep Research

Precision (P): 22. Result ID: 69e0955e47f34ce924c99f21.

[Reporting paper](<https://www.sota2.com/research/paper/69e06cfc7d0172140ec7c987.md>)

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

### FactCheckGPT

Precision (P): 21. Result ID: 69e0955e47f34ce924c99f1a.

[Reporting paper](<https://www.sota2.com/research/paper/69e06cfc7d0172140ec7c987.md>)

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

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