# Multimodal Mathematical Reasoning on MathVerse 1.0 (test) Source: [Multimodal Mathematical Reasoning on MathVerse 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-06-05T07:34:40.940Z Evaluation of model performance on the test split of MathVerse version 1.0, focusing on Multimodal Mathematical Reasoning capabilities. 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 1.0 (test) | | Metric | Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 17 of 17 | | 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 - [Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Score | Result date | Report paper | | --- | --- | --- | --- | | Vanilla (Full Tokens) | 73.01 | Not recorded | 69df1b747d0172140ec7b7e9 | | Vanilla (Full Tokens) | 62.81 | Not recorded | 69df1b747d0172140ec7b7e9 | | DSTP | 58.49 | Not recorded | 69df1b747d0172140ec7b7e9 | | DSTP | 51.16 | Not recorded | 69df1b747d0172140ec7b7e9 | | Vanilla (Full Tokens) | 47.89 | Not recorded | 69df1b747d0172140ec7b7e9 | | Vanilla (Full Tokens) | 47.46 | Not recorded | 69df1b747d0172140ec7b7e9 | | DSTP | 43.95 | Not recorded | 69df1b747d0172140ec7b7e9 | | FastV (33.3%) | 40.28 | Not recorded | 69df1b747d0172140ec7b7e9 | | VOLD | 37.9 | Not recorded | 69004e133ef7ccd74e5e2e75 | | FastV (33.3%) | 37.64 | Not recorded | 69df1b747d0172140ec7b7e9 | | DSTP | 37.25 | Not recorded | 69df1b747d0172140ec7b7e9 | | VLAA-Thinker 3B | 36.4 | Not recorded | 69004e133ef7ccd74e5e2e75 | | XReasoner-3B (repl.) | 35.7 | Not recorded | 69004e133ef7ccd74e5e2e75 | | VLM-R1 3B-Math | 32.2 | Not recorded | 69004e133ef7ccd74e5e2e75 | | FastV (33.3%) | 31.86 | Not recorded | 69df1b747d0172140ec7b7e9 | | Qwen2.5-VL-3B | 31.2 | Not recorded | 69004e133ef7ccd74e5e2e75 | | FastV (33.3%) | 18.48 | Not recorded | 69df1b747d0172140ec7b7e9 | ### Vanilla (Full Tokens) Score: 73.01. Result ID: 69df4d0a47f34ce924c8106f. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen3-VL-4B-Thinking","Model Category":"Thinking-based MLLMs","Token Retention Ratio":"100%"}. This record does not assert independent reproduction. ### Vanilla (Full Tokens) Score: 62.81. Result ID: 69df4d0a47f34ce924c81075. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen3-VL-8B","Model Category":"Large-scale MLLMs","Token Retention Ratio":"100%"}. This record does not assert independent reproduction. ### DSTP Score: 58.49. Result ID: 69df4d0a47f34ce924c81071. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-VL-4B-Thinking","Model Category":"Thinking-based MLLMs","Token Retention Ratio":"33.3%"}. This record does not assert independent reproduction. ### DSTP Score: 51.16. Result ID: 69df4d0a47f34ce924c81077. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-VL-8B","Model Category":"Large-scale MLLMs","Token Retention Ratio":"33.3%"}. This record does not assert independent reproduction. ### Vanilla (Full Tokens) Score: 47.89. Result ID: 69df4d0a47f34ce924c81078. [Reporting paper]() Recorded evaluation configuration: {"Model":"InternVL3.5-14B","Model Category":"Large-scale MLLMs","Token Retention Ratio":"100%"}. This record does not assert independent reproduction. ### Vanilla (Full Tokens) Score: 47.46. Result ID: 69df4d0a47f34ce924c81072. [Reporting paper]() Recorded evaluation configuration: {"Model":"InternVL3.5-8B-Thinking","Model Category":"Thinking-based MLLMs","Token Retention Ratio":"100%"}. This record does not assert independent reproduction. ### DSTP Score: 43.95. Result ID: 69df4d0a47f34ce924c8107a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"InternVL3.5-14B","Model Category":"Large-scale MLLMs","Token Retention Ratio":"33.3%"}. This record does not assert independent reproduction. ### FastV (33.3%) Score: 40.28. Result ID: 69df4d0a47f34ce924c81070. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-VL-4B-Thinking","Model Category":"Thinking-based MLLMs","Token Retention Ratio":"33.3%"}. This record does not assert independent reproduction. ### VOLD Score: 37.9. Result ID: 6a227bf5fbc373592c201f50. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Images in FT":"false"}. This record does not assert independent reproduction. ### FastV (33.3%) Score: 37.64. Result ID: 69df4d0a47f34ce924c81076. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-VL-8B","Model Category":"Large-scale MLLMs","Token Retention Ratio":"33.3%"}. This record does not assert independent reproduction. ### DSTP Score: 37.25. Result ID: 69df4d0a47f34ce924c81074. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"InternVL3.5-8B-Thinking","Model Category":"Thinking-based MLLMs","Token Retention Ratio":"33.3%"}. This record does not assert independent reproduction. ### VLAA-Thinker 3B Score: 36.4. Result ID: 6a227bf5fbc373592c201f4f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Images in FT":"true"}. This record does not assert independent reproduction. ### XReasoner-3B (repl.) Score: 35.7. Result ID: 6a227bf5fbc373592c201f4d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Images in FT":"false"}. This record does not assert independent reproduction. ### VLM-R1 3B-Math Score: 32.2. Result ID: 6a227bf5fbc373592c201f4e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Images in FT":"true"}. This record does not assert independent reproduction. ### FastV (33.3%) Score: 31.86. Result ID: 69df4d0a47f34ce924c81079. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"InternVL3.5-14B","Model Category":"Large-scale MLLMs","Token Retention Ratio":"33.3%"}. This record does not assert independent reproduction. ### Qwen2.5-VL-3B Score: 31.2. Result ID: 6a227bf5fbc373592c201f4c. [Reporting paper]() Recorded evaluation configuration: {"Images in FT":"-"}. This record does not assert independent reproduction. ### FastV (33.3%) Score: 18.48. Result ID: 69df4d0a47f34ce924c81073. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"InternVL3.5-8B-Thinking","Model Category":"Thinking-based MLLMs","Token Retention Ratio":"33.3%"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.