# Claim Verification on AVeriTeC Retrieved (H) (dev) Source: [Claim Verification on AVeriTeC Retrieved (H) (dev)]() Collection index: [llms.txt]() Data updated: 2026-04-06T07:09:15.193Z Evaluation of model performance on the development split of the AVeriTeC Retrieved (H) dataset for the Claim Verification task, reporting Accuracy and AVeriTeC Score. 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) | AVeriTeC Retrieved (H) (dev) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 28 of 28 | | 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 - [Accuracy](): Higher is better; unit: PERCENT. - [AVeriTeC Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | DebateCV | 72.8 | Not recorded | 68fa7a391e209131cea81e62 | | DebateCV | 72.6 | Not recorded | 68fa7a391e209131cea81e62 | | w/o Ccorrect | 70.8 | Not recorded | 68fa7a391e209131cea81e62 | | HerO | 70.2 | Not recorded | 68fa7a391e209131cea81e62 | | w/o Ccorrect | 69.4 | Not recorded | 68fa7a391e209131cea81e62 | | InFact | 68.6 | Not recorded | 68fa7a391e209131cea81e62 | | HerO | 68.2 | Not recorded | 68fa7a391e209131cea81e62 | | Cooperation | 67.6 | Not recorded | 68fa7a391e209131cea81e62 | | w/o Debate-SFT | 65.4 | Not recorded | 68fa7a391e209131cea81e62 | | InFact | 65.2 | Not recorded | 68fa7a391e209131cea81e62 | | Cooperation | 65.2 | Not recorded | 68fa7a391e209131cea81e62 | | Majority | 64.4 | Not recorded | 68fa7a391e209131cea81e62 | | CoT | 63.8 | Not recorded | 68fa7a391e209131cea81e62 | | Majority | 63.8 | Not recorded | 68fa7a391e209131cea81e62 | | Majority | 63.8 | Not recorded | 68fa7a391e209131cea81e62 | | InFact | 63.6 | Not recorded | 68fa7a391e209131cea81e62 | | Majority | 63.6 | Not recorded | 68fa7a391e209131cea81e62 | | InFact | 63.4 | Not recorded | 68fa7a391e209131cea81e62 | | w/o Cerror | 63 | Not recorded | 68fa7a391e209131cea81e62 | | w/o Cerror | 62.9 | Not recorded | 68fa7a391e209131cea81e62 | | CoT | 62.8 | Not recorded | 68fa7a391e209131cea81e62 | | CoT | 62.6 | Not recorded | 68fa7a391e209131cea81e62 | | CoT | 62.4 | Not recorded | 68fa7a391e209131cea81e62 | | Cooperation | 61.2 | Not recorded | 68fa7a391e209131cea81e62 | | Cooperation | 60.8 | Not recorded | 68fa7a391e209131cea81e62 | | w/o Debate-SFT | 54.8 | Not recorded | 68fa7a391e209131cea81e62 | | w/o Debate-SFT | 54.2 | Not recorded | 68fa7a391e209131cea81e62 | | w/o Debate-SFT | 53.8 | Not recorded | 68fa7a391e209131cea81e62 | ### DebateCV Accuracy: 72.8. Result ID: 69d35bfd47f34ce924baaf6a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLMs":"Llama-3.1-8B"}. This record does not assert independent reproduction. ### DebateCV Accuracy: 72.6. Result ID: 69d35bfd47f34ce924baaf6b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLMs":"Qwen-2.5-7B"}. This record does not assert independent reproduction. ### w/o Ccorrect Accuracy: 70.8. Result ID: 69d35bfd47f34ce924baaf6e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLMs":"Llama-3.1-8B"}. This record does not assert independent reproduction. ### HerO Accuracy: 70.2. Result ID: 69d35bfd47f34ce924baaf60. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LLMs":"Llama-3.1-8B"}. This record does not assert independent reproduction. ### w/o Ccorrect Accuracy: 69.4. Result ID: 69d35bfd47f34ce924baaf6f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLMs":"Qwen-2.5-7B"}. This record does not assert independent reproduction. ### InFact Accuracy: 68.6. Result ID: 69d35bfd47f34ce924baaf5c. [Reporting paper]() Recorded evaluation configuration: {"LLMs":"GPT-4o"}. This record does not assert independent reproduction. ### HerO Accuracy: 68.2. Result ID: 69d35bfd47f34ce924baaf61. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LLMs":"Qwen-2.5-7B"}. This record does not assert independent reproduction. ### Cooperation Accuracy: 67.6. Result ID: 69d35bfd47f34ce924baaf66. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLMs":"GPT-4o"}. This record does not assert independent reproduction. ### w/o Debate-SFT Accuracy: 65.4. Result ID: 69d35bfd47f34ce924baaf70. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLMs":"GPT-4o"}. This record does not assert independent reproduction. ### InFact Accuracy: 65.2. Result ID: 69d35bfd47f34ce924baaf5d. [Reporting paper]() Recorded evaluation configuration: {"LLMs":"GPT-4o-Mini"}. This record does not assert independent reproduction. ### Cooperation Accuracy: 65.2. Result ID: 69d35bfd47f34ce924baaf67. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLMs":"GPT-4o-Mini"}. This record does not assert independent reproduction. ### Majority Accuracy: 64.4. Result ID: 69d35bfd47f34ce924baaf62. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLMs":"GPT-4o"}. This record does not assert independent reproduction. ### CoT Accuracy: 63.8. Result ID: 69d35bfd47f34ce924baaf58. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLMs":"GPT-4o"}. This record does not assert independent reproduction. ### Majority Accuracy: 63.8. Result ID: 69d35bfd47f34ce924baaf63. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLMs":"GPT-4o-Mini"}. This record does not assert independent reproduction. ### Majority Accuracy: 63.8. Result ID: 69d35bfd47f34ce924baaf64. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLMs":"Llama-3.1-8B"}. This record does not assert independent reproduction. ### InFact Accuracy: 63.6. Result ID: 69d35bfd47f34ce924baaf5f. [Reporting paper]() Recorded evaluation configuration: {"LLMs":"Qwen-2.5-7B"}. This record does not assert independent reproduction. ### Majority Accuracy: 63.6. Result ID: 69d35bfd47f34ce924baaf65. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLMs":"Qwen-2.5-7B"}. This record does not assert independent reproduction. ### InFact Accuracy: 63.4. Result ID: 69d35bfd47f34ce924baaf5e. [Reporting paper]() Recorded evaluation configuration: {"LLMs":"Llama-3.1-8B"}. This record does not assert independent reproduction. ### w/o Cerror Accuracy: 63. Result ID: 69d35bfd47f34ce924baaf6c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLMs":"Llama-3.1-8B"}. This record does not assert independent reproduction. ### w/o Cerror Accuracy: 62.9. Result ID: 69d35bfd47f34ce924baaf6d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLMs":"Qwen-2.5-7B"}. This record does not assert independent reproduction. ### CoT Accuracy: 62.8. Result ID: 69d35bfd47f34ce924baaf59. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLMs":"GPT-4o-Mini"}. This record does not assert independent reproduction. ### CoT Accuracy: 62.6. Result ID: 69d35bfd47f34ce924baaf5b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLMs":"Qwen-2.5-7B"}. This record does not assert independent reproduction. ### CoT Accuracy: 62.4. Result ID: 69d35bfd47f34ce924baaf5a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLMs":"Llama-3.1-8B"}. This record does not assert independent reproduction. ### Cooperation Accuracy: 61.2. Result ID: 69d35bfd47f34ce924baaf68. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLMs":"Llama-3.1-8B"}. This record does not assert independent reproduction. ### Cooperation Accuracy: 60.8. Result ID: 69d35bfd47f34ce924baaf69. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLMs":"Qwen-2.5-7B"}. This record does not assert independent reproduction. ### w/o Debate-SFT Accuracy: 54.8. Result ID: 69d35bfd47f34ce924baaf71. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLMs":"GPT-4o-Mini"}. This record does not assert independent reproduction. ### w/o Debate-SFT Accuracy: 54.2. Result ID: 69d35bfd47f34ce924baaf73. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLMs":"Qwen-2.5-7B"}. This record does not assert independent reproduction. ### w/o Debate-SFT Accuracy: 53.8. Result ID: 69d35bfd47f34ce924baaf72. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLMs":"Llama-3.1-8B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.