# Uncertainty Quantification on MATH (PRR) Source: [Uncertainty Quantification on MATH (PRR)]() Collection index: [llms.txt]() Data updated: 2026-06-11T06:44:57.370Z Evaluation of model uncertainty quantification performance on the MATH dataset, measured using PRR. 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 | Uncertainty Quantification | | Dataset (including any stated split) | MATH | | Metric | PRR | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 - [PRR](): Higher is better; unit: PERCENT. ## Recorded results | Method | PRR | Result date | Report paper | | --- | --- | --- | --- | | GLU-Sα-SP | 70 | Not recorded | 6a28f33c90966ade919c16f5 | | GLU | 69.9 | Not recorded | 6a28f33c90966ade919c16f5 | | LogTokU | 69.3 | Not recorded | 6a28f33c90966ade919c16f5 | | GLU-AU | 64.8 | Not recorded | 6a28f33c90966ade919c16f5 | | RAUQ | 63.9 | Not recorded | 6a28f33c90966ade919c16f5 | | P(true) | 63.6 | Not recorded | 6a28f33c90966ade919c16f5 | | GLU | 62.7 | Not recorded | 6a28f33c90966ade919c16f5 | | RAUQ | 62.4 | Not recorded | 6a28f33c90966ade919c16f5 | | P(true) | 57.4 | Not recorded | 6a28f33c90966ade919c16f5 | | GLU-Sα-SP | 54.5 | Not recorded | 6a28f33c90966ade919c16f5 | | GLU | 53.7 | Not recorded | 6a28f33c90966ade919c16f5 | | LogProb | 52 | Not recorded | 6a28f33c90966ade919c16f5 | | LogProb | 43.8 | Not recorded | 6a28f33c90966ade919c16f5 | | RAUQ | 42.4 | Not recorded | 6a28f33c90966ade919c16f5 | | LogProb | 38.1 | Not recorded | 6a28f33c90966ade919c16f5 | | P(true) | 32.5 | Not recorded | 6a28f33c90966ade919c16f5 | | LogTokU | 32.4 | Not recorded | 6a28f33c90966ade919c16f5 | | LogTokU | 21.6 | Not recorded | 6a28f33c90966ade919c16f5 | ### GLU-Sα-SP PRR: 70. Result ID: 6a2a5959fbc373592c26cc90. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Gemma"}. This record does not assert independent reproduction. ### GLU PRR: 69.9. Result ID: 6a2a5959fbc373592c26cc8f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Gemma"}. This record does not assert independent reproduction. ### LogTokU PRR: 69.3. Result ID: 6a2a5959fbc373592c26cc8b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Gemma"}. This record does not assert independent reproduction. ### GLU-AU PRR: 64.8. Result ID: 6a2a5959fbc373592c26cc96. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Fanar"}. This record does not assert independent reproduction. ### RAUQ PRR: 63.9. Result ID: 6a2a5959fbc373592c26cc8c. [Reporting paper]() Recorded evaluation configuration: {"Model":"Gemma"}. This record does not assert independent reproduction. ### P(true) PRR: 63.6. Result ID: 6a2a5959fbc373592c26cc8e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Gemma"}. This record does not assert independent reproduction. ### GLU PRR: 62.7. Result ID: 6a2a5959fbc373592c26cc95. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Fanar"}. This record does not assert independent reproduction. ### RAUQ PRR: 62.4. Result ID: 6a2a5959fbc373592c26cc92. [Reporting paper]() Recorded evaluation configuration: {"Model":"Fanar"}. This record does not assert independent reproduction. ### P(true) PRR: 57.4. Result ID: 6a2a5959fbc373592c26cc88. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen"}. This record does not assert independent reproduction. ### GLU-Sα-SP PRR: 54.5. Result ID: 6a2a5959fbc373592c26cc8a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen"}. This record does not assert independent reproduction. ### GLU PRR: 53.7. Result ID: 6a2a5959fbc373592c26cc89. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen"}. This record does not assert independent reproduction. ### LogProb PRR: 52. Result ID: 6a2a5959fbc373592c26cc93. [Reporting paper]() Recorded evaluation configuration: {"Model":"Fanar"}. This record does not assert independent reproduction. ### LogProb PRR: 43.8. Result ID: 6a2a5959fbc373592c26cc8d. [Reporting paper]() Recorded evaluation configuration: {"Model":"Gemma"}. This record does not assert independent reproduction. ### RAUQ PRR: 42.4. Result ID: 6a2a5959fbc373592c26cc86. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen"}. This record does not assert independent reproduction. ### LogProb PRR: 38.1. Result ID: 6a2a5959fbc373592c26cc87. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen"}. This record does not assert independent reproduction. ### P(true) PRR: 32.5. Result ID: 6a2a5959fbc373592c26cc94. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Fanar"}. This record does not assert independent reproduction. ### LogTokU PRR: 32.4. Result ID: 6a2a5959fbc373592c26cc91. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Fanar"}. This record does not assert independent reproduction. ### LogTokU PRR: 21.6. Result ID: 6a2a5959fbc373592c26cc85. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.