# Mathematical Reasoning on HLE Math-text (Pass@1) Source: [Mathematical Reasoning on HLE Math-text (Pass@1)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:57:24.596Z Evaluation of model performance on mathematical reasoning problems using the HLE Math-text dataset, specifically measured using the Pass@1 metric. 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 | Mathematical Reasoning | | Dataset (including any stated split) | HLE Math-text | | Metric | Pass@1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 - [Pass@1](): Higher is better; unit: PERCENT. ## Recorded results | Method | Pass@1 | Result date | Report paper | | --- | --- | --- | --- | | RSE | 62.8 | Not recorded | 697c3b5ba8b01e76cc8da658 | | RSE | 59.2 | Not recorded | 697c3b5ba8b01e76cc8da658 | | MV@128 | 58.4 | Not recorded | 697c3b5ba8b01e76cc8da658 | | PaCoRe | 58.1 | Not recorded | 697c3b5ba8b01e76cc8da658 | | PaCoRe | 57.9 | Not recorded | 697c3b5ba8b01e76cc8da658 | | Base | 49.3 | Not recorded | 697c3b5ba8b01e76cc8da658 | | PaCoRe | 49.3 | Not recorded | 697c3b5ba8b01e76cc8da658 | | RSE | 49.3 | Not recorded | 697c3b5ba8b01e76cc8da658 | | RSE | 44.8 | Not recorded | 697c3b5ba8b01e76cc8da658 | | Base | 24 | Not recorded | 697c3b5ba8b01e76cc8da658 | | RSE | 11.4 | Not recorded | 697c3b5ba8b01e76cc8da658 | | Base | 8.5 | Not recorded | 697c3b5ba8b01e76cc8da658 | ### RSE Pass@1: 62.8. Result ID: 699662d85698665ec4a8f2c4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Deepseek-V3.2","Iteration":"It2"}. This record does not assert independent reproduction. ### RSE Pass@1: 59.2. Result ID: 699662d85698665ec4a8f2c3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Deepseek-V3.2","Iteration":"It1"}. This record does not assert independent reproduction. ### MV@128 Pass@1: 58.4. Result ID: 699662d85698665ec4a8f2be. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Deepseek-V3.2","Iteration":"It0"}. This record does not assert independent reproduction. ### PaCoRe Pass@1: 58.1. Result ID: 699662d85698665ec4a8f2c0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Deepseek-V3.2","Iteration":"It1"}. This record does not assert independent reproduction. ### PaCoRe Pass@1: 57.9. Result ID: 699662d85698665ec4a8f2c1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Deepseek-V3.2","Iteration":"It2"}. This record does not assert independent reproduction. ### Base Pass@1: 49.3. Result ID: 699662d85698665ec4a8f2bd. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Deepseek-V3.2","Iteration":"It0"}. This record does not assert independent reproduction. ### PaCoRe Pass@1: 49.3. Result ID: 699662d85698665ec4a8f2bf. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Deepseek-V3.2","Iteration":"It0"}. This record does not assert independent reproduction. ### RSE Pass@1: 49.3. Result ID: 699662d85698665ec4a8f2c2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Deepseek-V3.2","Iteration":"It0"}. This record does not assert independent reproduction. ### RSE Pass@1: 44.8. Result ID: 699662d85698665ec4a8f2e3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-30B-A3B-Thinking-2507","Inference Strategy":"Recycling Search Experience","Iteration":"It3"}. This record does not assert independent reproduction. ### Base Pass@1: 24. Result ID: 699662d85698665ec4a8f2e2. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-30B-A3B-Thinking-2507","Inference Strategy":"Standard Sampling","Iteration":"It0"}. This record does not assert independent reproduction. ### RSE Pass@1: 11.4. Result ID: 699662d85698665ec4a8f2e5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Phi-4-Reasoning","Inference Strategy":"Recycling Search Experience","Iteration":"It3"}. This record does not assert independent reproduction. ### Base Pass@1: 8.5. Result ID: 699662d85698665ec4a8f2e4. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Phi-4-Reasoning","Inference Strategy":"Standard Sampling","Iteration":"It0"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.