# Question Answering on TriviaQA (TriviaQA, Average) Source: [Question Answering on TriviaQA (TriviaQA, Average)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:07:42.791Z Evaluation of model performance on the TriviaQA dataset for Question Answering, reporting the custom metrics 'TriviaQA' score and '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 | Question Answering | | Dataset (including any stated split) | TriviaQA | | Metric | TriviaQA Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 11 of 11 | | 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 - [TriviaQA Score](): Higher is better; unit: PERCENT. - [Average Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | TriviaQA Score | Result date | Report paper | | --- | --- | --- | --- | | LLM-PeerReview | 77.3 | Not recorded | 69535c9353fdd5c36173da4e | | LLM-PeerReview-W | 77.3 | Not recorded | 69535c9353fdd5c36173da4e | | Smoothie-Local | 74 | Not recorded | 69535c9353fdd5c36173da4e | | Qwen2.5-14B-Instruct | 73.5 | Not recorded | 69535c9353fdd5c36173da4e | | Smoothie-Global | 73.5 | Not recorded | 69535c9353fdd5c36173da4e | | Agent-Forest | 73 | Not recorded | 69535c9353fdd5c36173da4e | | Qwen2.5-14B-Instruct-1M | 69.5 | Not recorded | 69535c9353fdd5c36173da4e | | Phi-3-medium-4k-instruct | 68 | Not recorded | 69535c9353fdd5c36173da4e | | Random | 67.7 | Not recorded | 69535c9353fdd5c36173da4e | | Theoretical average | 67.6 | Not recorded | 69535c9353fdd5c36173da4e | | DeepSeek-R1-Distill-Qwen-14B | 59.5 | Not recorded | 69535c9353fdd5c36173da4e | ### LLM-PeerReview TriviaQA Score: 77.3. Result ID: 6996ac995698665ec4f6aae1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LLM-PeerReview-W TriviaQA Score: 77.3. Result ID: 6996ac995698665ec4f6aae2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Smoothie-Local TriviaQA Score: 74. Result ID: 6996ac995698665ec4f6aadf. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Scope":"Local"}. This record does not assert independent reproduction. ### Qwen2.5-14B-Instruct TriviaQA Score: 73.5. Result ID: 6996ac995698665ec4f6aad8. [Reporting paper]() Recorded evaluation configuration: {"Scale":"13B-14B"}. This record does not assert independent reproduction. ### Smoothie-Global TriviaQA Score: 73.5. Result ID: 6996ac995698665ec4f6aade. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Scope":"Global"}. This record does not assert independent reproduction. ### Agent-Forest TriviaQA Score: 73. Result ID: 6996ac995698665ec4f6aae0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen2.5-14B-Instruct-1M TriviaQA Score: 69.5. Result ID: 6996ac995698665ec4f6aada. [Reporting paper]() Recorded evaluation configuration: {"Scale":"13B-14B"}. This record does not assert independent reproduction. ### Phi-3-medium-4k-instruct TriviaQA Score: 68. Result ID: 6996ac995698665ec4f6aadb. [Reporting paper]() Recorded evaluation configuration: {"Scale":"13B-14B"}. This record does not assert independent reproduction. ### Random TriviaQA Score: 67.7. Result ID: 6996ac995698665ec4f6aadd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Theoretical average TriviaQA Score: 67.6. Result ID: 6996ac995698665ec4f6aadc. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DeepSeek-R1-Distill-Qwen-14B TriviaQA Score: 59.5. Result ID: 6996ac995698665ec4f6aad9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"13B-14B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.