# Factual Recall on TriviaQA Source: [Factual Recall on TriviaQA]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:31:07.403Z Evaluation of model performance on the TriviaQA dataset specifically for factual recall tasks, measured using Accuracy and an Average 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 | Factual Recall | | Dataset (including any stated split) | TriviaQA | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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. - [Average Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | LLM-PeerReview-W | 77 | Not recorded | 69535c9353fdd5c36173da4e | | LLM-PeerReview | 76.9 | Not recorded | 69535c9353fdd5c36173da4e | | Llama-3.1-8B-Selection | 76.5 | Not recorded | 69535c9353fdd5c36173da4e | | Mistral-7B-Selection | 75.6 | Not recorded | 69535c9353fdd5c36173da4e | | Qwen2.5-7B-Selection | 75.5 | Not recorded | 69535c9353fdd5c36173da4e | | Llama-3.1-8B-Instruct | 75.3 | Not recorded | 69535c9353fdd5c36173da4e | | Qwen2-7B-Selection | 74.2 | Not recorded | 69535c9353fdd5c36173da4e | | Smoothie-Local | 73.6 | Not recorded | 69535c9353fdd5c36173da4e | | Mistral-7B-Instruct | 72.7 | Not recorded | 69535c9353fdd5c36173da4e | | GaC | 71.5 | Not recorded | 69535c9353fdd5c36173da4e | | Agent-Forest | 70.5 | Not recorded | 69535c9353fdd5c36173da4e | | Theoretical average | 68.4 | Not recorded | 69535c9353fdd5c36173da4e | | Random | 68.4 | Not recorded | 69535c9353fdd5c36173da4e | | Qwen2-7B-Instruct | 63 | Not recorded | 69535c9353fdd5c36173da4e | | Smoothie-Global | 63 | Not recorded | 69535c9353fdd5c36173da4e | | Qwen2.5-7B-Instruct | 62.5 | Not recorded | 69535c9353fdd5c36173da4e | ### LLM-PeerReview-W Accuracy: 77. Result ID: 6996ac995698665ec4f6aaf9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"LLM Ensemble"}. This record does not assert independent reproduction. ### LLM-PeerReview Accuracy: 76.9. Result ID: 6996ac995698665ec4f6aaf8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"LLM Ensemble"}. This record does not assert independent reproduction. ### Llama-3.1-8B-Selection Accuracy: 76.5. Result ID: 6996ac995698665ec4f6aafa. [Reporting paper]() Recorded evaluation configuration: {"Type":"Our variants"}. This record does not assert independent reproduction. ### Mistral-7B-Selection Accuracy: 75.6. Result ID: 6996ac995698665ec4f6aafb. [Reporting paper]() Recorded evaluation configuration: {"Type":"Our variants"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Selection Accuracy: 75.5. Result ID: 6996ac995698665ec4f6aafd. [Reporting paper]() Recorded evaluation configuration: {"Type":"Our variants"}. This record does not assert independent reproduction. ### Llama-3.1-8B-Instruct Accuracy: 75.3. Result ID: 6996ac995698665ec4f6aaee. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"Single LLM"}. This record does not assert independent reproduction. ### Qwen2-7B-Selection Accuracy: 74.2. Result ID: 6996ac995698665ec4f6aafc. [Reporting paper]() Recorded evaluation configuration: {"Type":"Our variants"}. This record does not assert independent reproduction. ### Smoothie-Local Accuracy: 73.6. Result ID: 6996ac995698665ec4f6aaf5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"LLM Ensemble"}. This record does not assert independent reproduction. ### Mistral-7B-Instruct Accuracy: 72.7. Result ID: 6996ac995698665ec4f6aaef. [Reporting paper]() Recorded evaluation configuration: {"Type":"Single LLM"}. This record does not assert independent reproduction. ### GaC Accuracy: 71.5. Result ID: 6996ac995698665ec4f6aaf7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"LLM Ensemble"}. This record does not assert independent reproduction. ### Agent-Forest Accuracy: 70.5. Result ID: 6996ac995698665ec4f6aaf6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"LLM Ensemble"}. This record does not assert independent reproduction. ### Theoretical average Accuracy: 68.4. Result ID: 6996ac995698665ec4f6aaf2. [Reporting paper]() Recorded evaluation configuration: {"Type":"Single LLM"}. This record does not assert independent reproduction. ### Random Accuracy: 68.4. Result ID: 6996ac995698665ec4f6aaf3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"LLM Ensemble"}. This record does not assert independent reproduction. ### Qwen2-7B-Instruct Accuracy: 63. Result ID: 6996ac995698665ec4f6aaf0. [Reporting paper]() Recorded evaluation configuration: {"Type":"Single LLM"}. This record does not assert independent reproduction. ### Smoothie-Global Accuracy: 63. Result ID: 6996ac995698665ec4f6aaf4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"LLM Ensemble"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct Accuracy: 62.5. Result ID: 6996ac995698665ec4f6aaf1. [Reporting paper]() Recorded evaluation configuration: {"Type":"Single LLM"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.