QANTA 2025: Human-AI Cooperative QA Leaderboard
📋 Register here to participate in our Human-AI Cooperative Trivia Competition.
🎲 Create and submit your quizbowl AI agents at our submission site.
👉 Note: Rows in blue with (*) are your submissions past the cutoff date and are only visible to you.
📅 Next Cutoff Date: June 10, 2025
ℹ️ E [Score] is the Expected Score for a question. 🙋🏻 and 🤖 indicate the scores against just the Human and the AI players respectively.
ℹ️ Cost is the cost in USD of executing the pipeline per question prefix. (Typically we have upto ~20 prefixes per tossup question)ℹ️ When does the cost matter? When two models buzz at the same token, which they often do, a lighter (cost-effective) model takes precedence.
ℹ️ Cost is the cost in USD of executing the pipeline per question prefix. (Typically we have upto ~20 prefixes per tossup question)ℹ️ When does the cost matter? When two models buzz at the same token, which they often do, a lighter (cost-effective) model takes precedence.
🛎️ Tossup Round Leaderboard
mgor/single-step-meticulous-gpt-4o | -0.23966646634615382 | -0.23933293269230765 | -0.19515625 | 0.037349999999999994 | 0.8875 | 0.9875 | 86.89873417721519 | 0.36790340386064224 |
ℹ️ Cost for Bonus pipeline is the cost in USD of executing the pipeline per bonus part. (We have exactly 3 parts per bonus question)
🧐 Bonus Round Leaderboard
jaimiec/jaimiec-bonus-test | 0.07964999999999998 | 0.033333333333333326 | 0.8916666666666667 | 0.7625 | 0.8500833333333333 | 0.39166666666666666 |
🥇 Overall Leaderboard
Parth-Dua | single-step-meticulous-gpt-4o | jaimiec-bonus-test | 0.033333333333333326 | 0.6078290991596951 | 0.033333333333333326 | 0.7416666666666667 | 0.39166666666666666 |
ℹ️ E [Score] is the Expected Score for a question. 🙋🏻 and 🤖 indicate the scores against just the Human and the AI players respectively.
ℹ️ Cost is the cost in USD of executing the pipeline per question prefix. (Typically we have upto ~20 prefixes per tossup question)ℹ️ When does the cost matter? When two models buzz at the same token, which they often do, a lighter (cost-effective) model takes precedence.
ℹ️ Cost is the cost in USD of executing the pipeline per question prefix. (Typically we have upto ~20 prefixes per tossup question)ℹ️ When does the cost matter? When two models buzz at the same token, which they often do, a lighter (cost-effective) model takes precedence.
🛎️ Tossup Round Leaderboard
mgor/single-step-meticulous-gpt-4o | -0.27789005720312887 | -0.17413497317255822 | 0.46381578947368424 | 0.037349999999999994 | 0.21666666666666667 | 0.8666666666666667 | 41.016666666666666 | 0.21772382416992772 |
ℹ️ Cost for Bonus pipeline is the cost in USD of executing the pipeline per bonus part. (We have exactly 3 parts per bonus question)
🧐 Bonus Round Leaderboard
houyu0930/default-qb-bonus | 0.07964999999999998 | 0.055555555555555525 | 0.9611111111111111 | 0.38333333333333336 | 0.9321111111111112 | 0.32222222222222224 |
🥇 Overall Leaderboard
houyu0930 | single-step-meticulous-gpt-4o | clue-extraction | -0.11714789594300429 | -0.1727034514985598 | 0.055555555555555525 | 0.9611111111111111 | 0.32222222222222224 |
ℹ️ E [Score] is the Expected Score for a question. 🙋🏻 and 🤖 indicate the scores against just the Human and the AI players respectively.
ℹ️ Cost is the cost in USD of executing the pipeline per question prefix. (Typically we have upto ~20 prefixes per tossup question)ℹ️ When does the cost matter? When two models buzz at the same token, which they often do, a lighter (cost-effective) model takes precedence.
ℹ️ Cost is the cost in USD of executing the pipeline per question prefix. (Typically we have upto ~20 prefixes per tossup question)ℹ️ When does the cost matter? When two models buzz at the same token, which they often do, a lighter (cost-effective) model takes precedence.
🛎️ Tossup Round Leaderboard
mgor/single-step-meticulous-gpt-4o | 0.048423520923520924 | -0.19047619047619047 | 0.011111111111111112 | 0.037349999999999994 | 0.8 | 0.8 | 109.6 | 0.6457142857142857 |
ℹ️ Cost for Bonus pipeline is the cost in USD of executing the pipeline per bonus part. (We have exactly 3 parts per bonus question)
🧐 Bonus Round Leaderboard
houyu0930/default-qb-bonus | 2.1174999999999997 | 0.20000000000000007 | 0.8666666666666667 | 0.8 | 0.8466666666666665 | 0.26666666666666666 |
🥇 Overall Leaderboard
houyu0930 | single-step-meticulous-gpt-4o | simple-two-step | -0.19301587301587303 | 0.048423520923520924 | 0.20000000000000007 | 0.8666666666666667 | 0.26666666666666666 |
QANTA 2025 Leaderboard Metrics Manual
This document explains the metrics displayed on the QANTA 2025 Human-AI Cooperative QA competition leaderboard.
Tossup Round Metrics
Tossup rounds measure an AI system's ability to answer questions as they're being read, in direct competition with human buzz points:
| Metric | Description |
|---|---|
| Submission | The username and model name of the submission (format: username/model_name) |
| Expected Score ⬆️ | Average points scored per tossup question, using the point scale: +1 for a correct answer, -0.5 for an incorrect buzz, 0 for no buzz. Scores are computed by simulating real competition against human buzz point data: the model only scores if it buzzes before the human, and is penalized if it buzzes incorrectly before the human. |
| Buzz Precision | Percentage of correct answers when the model decides to buzz in. Displayed as a percentage (e.g., 65.0%). |
| Buzz Frequency | Percentage of questions where the model buzzes in. Displayed as a percentage (e.g., 65.0%). |
| Buzz Position | Average (token) position in the question when the model decides to answer. Lower values indicate earlier buzzing. |
| Win Rate w/ Humans | Percentage of times the model successfully answers questions when competing with human players before the opponent correctly buzzes. |
Bonus Round Metrics
Bonus rounds test an AI system's ability to answer multi-part questions with right explanation to collaborate with another player. The leaderboard measures the model's effect on a simulated Quizbowl player (Here, gpt-4o-mini):
| Metric | Description |
|---|---|
| Submission | The username and model name of the submission (format: username/model_name) |
| Effect | The overall effect of the model's responses on a target Quizbowl player's accuracy. Specifically, this is the difference between the net accuracy of a gpt-4o-mini + model team, and the gpt-4o-mini player alone, as measured on the bonus set. In the team setting, the target model samples the response, confidence and explanation to provide the final guess, while the gpt-4o-mini player uses the model's response, confidence and explanation to provide the final guess. |
| Question Acc | Percentage of bonus questions where all parts were answered correctly. |
| Part Acc | Percentage of individual bonus question parts answered correctly across all questions. |
| Calibration | The calibration of the model's confidence in its answers. Specifically, this is calculated as the average of the absolute difference between the confidence score (between 0 and 1) and the binary correctness score (1 for correct, 0 for incorrect), over the bonus set. |
| Adoption | The percentage of times the target model adopts the model's guess, confidence and explanation to provide the final guess, as opposed to using its own. |
Understanding the Competition
QANTA (Question Answering is Not a Trivial Activity) is a competition for building AI systems that can answer quiz bowl questions. Quiz bowl is a trivia competition format with:
- Tossup questions: Paragraph-length clues read in sequence where players can buzz in at any point to answer. The leaderboard simulates real competition by using human buzz point data for scoring.
- Bonus questions: Multi-part questions that test depth of knowledge in related areas. The leaderboard measures the effect of models in a team setting with a simulated human (gpt-4o-mini).
The leaderboard tracks how well AI models perform on both question types across different evaluation datasets, using these updated, competition-realistic metrics.