# Multimodal Mathematical Reasoning on MathVerse (Pass@1 Accuracy) Source: [Multimodal Mathematical Reasoning on MathVerse (Pass@1 Accuracy)]() Collection index: [llms.txt]() Data updated: 2026-04-14T08:50:59.799Z Evaluation of model performance on the base MathVerse dataset for Multimodal Mathematical Reasoning, specifically reporting Pass@1 accuracy. 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 | Multimodal Mathematical Reasoning | | Dataset (including any stated split) | MathVerse | | Metric | Pass@1 Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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 Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Pass@1 Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Qwen2.5-VL-7B-Instruct + RFT | 47.2 | Not recorded | 69ddca347d0172140ec79b4e | | Claude-3.5-Sonnet | 44.2 | Not recorded | 69ddca347d0172140ec79b4e | | Qwen2.5-VL-7B-Instruct + cold start | 44.1 | Not recorded | 69ddca347d0172140ec79b4e | | Qwen2.5-VL-7B-Instruct | 43.9 | Not recorded | 69ddca347d0172140ec79b4e | | Qwen2.5-VL-7B-Instruct | 43.3 | Not recorded | 69ddca347d0172140ec79b4e | | Qwen2.5-VL-7B-Instruct | 43.3 | Not recorded | 69ddca347d0172140ec79b4e | | GPT-4o-20240513 | 40.6 | Not recorded | 69ddca347d0172140ec79b4e | | InternVL3-9B | 35.3 | Not recorded | 69ddca347d0172140ec79b4e | | Gemini-1.5-Pro | 30.1 | Not recorded | 69ddca347d0172140ec79b4e | | Qwen2-VL-7B | 30.1 | Not recorded | 69ddca347d0172140ec79b4e | | LLaVA-OneVision-72B | 27.2 | Not recorded | 69ddca347d0172140ec79b4e | | InternVL2.5-26B | 24 | Not recorded | 69ddca347d0172140ec79b4e | | InternVL2.5-8B | 22.8 | Not recorded | 69ddca347d0172140ec79b4e | | MiniCPM-V2.6 | 18.9 | Not recorded | 69ddca347d0172140ec79b4e | ### Qwen2.5-VL-7B-Instruct + RFT Pass@1 Accuracy: 47.2. Result ID: 69ddffa047f34ce924c5829c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Source Category":"Ours","Training Strategy":"RFT"}. This record does not assert independent reproduction. ### Claude-3.5-Sonnet Pass@1 Accuracy: 44.2. Result ID: 69ddffa047f34ce924c58290. [Reporting paper]() Recorded evaluation configuration: {"Model Source Category":"Closed-Source Models"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B-Instruct + cold start Pass@1 Accuracy: 44.1. Result ID: 69ddffa047f34ce924c5829b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Source Category":"Ours","Training Strategy":"cold start"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B-Instruct Pass@1 Accuracy: 43.9. Result ID: 69ddffa047f34ce924c58299. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Source Category":"Base Model","Chain-of-Thought (CoT)":"true"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B-Instruct Pass@1 Accuracy: 43.3. Result ID: 69ddffa047f34ce924c58298. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Source Category":"Base Model"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B-Instruct Pass@1 Accuracy: 43.3. Result ID: 69ddffa047f34ce924c5829a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Source Category":"Ours"}. This record does not assert independent reproduction. ### GPT-4o-20240513 Pass@1 Accuracy: 40.6. Result ID: 69ddffa047f34ce924c5828f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Source Category":"Closed-Source Models"}. This record does not assert independent reproduction. ### InternVL3-9B Pass@1 Accuracy: 35.3. Result ID: 69ddffa047f34ce924c58294. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Source Category":"Open-Source Models"}. This record does not assert independent reproduction. ### Gemini-1.5-Pro Pass@1 Accuracy: 30.1. Result ID: 69ddffa047f34ce924c58291. [Reporting paper]() Recorded evaluation configuration: {"Model Source Category":"Closed-Source Models"}. This record does not assert independent reproduction. ### Qwen2-VL-7B Pass@1 Accuracy: 30.1. Result ID: 69ddffa047f34ce924c58295. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Source Category":"Open-Source Models"}. This record does not assert independent reproduction. ### LLaVA-OneVision-72B Pass@1 Accuracy: 27.2. Result ID: 69ddffa047f34ce924c58296. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Source Category":"Open-Source Models"}. This record does not assert independent reproduction. ### InternVL2.5-26B Pass@1 Accuracy: 24. Result ID: 69ddffa047f34ce924c58297. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Source Category":"Open-Source Models"}. This record does not assert independent reproduction. ### InternVL2.5-8B Pass@1 Accuracy: 22.8. Result ID: 69ddffa047f34ce924c58292. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Source Category":"Open-Source Models"}. This record does not assert independent reproduction. ### MiniCPM-V2.6 Pass@1 Accuracy: 18.9. Result ID: 69ddffa047f34ce924c58293. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Source Category":"Open-Source Models"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.