# Multilingual text-centric visual question answering on MTVQA Source: [Multilingual text-centric visual question answering on MTVQA]() Collection index: [llms.txt]() Data updated: 2026-04-15T07:16:46.206Z Evaluation of model performance on the MTVQA dataset for multilingual text-centric visual question answering. 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 | Multilingual text-centric visual question answering | | Dataset (including any stated split) | MTVQA | | Metric | Average Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 56 of 56 | | 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 - [Average Score](): Higher is better; unit: PERCENT. - [Score (ar)](): Higher is better; unit: PERCENT. - [Score (de)](): Higher is better; unit: PERCENT. - [Score (fr)](): Higher is better; unit: PERCENT. - [Score (it)](): Higher is better; unit: PERCENT. - [Score (ja)](): Higher is better; unit: PERCENT. - [Score (ko)](): Higher is better; unit: PERCENT. - [Score (ru)](): Higher is better; unit: PERCENT. - [Score (th)](): Higher is better; unit: PERCENT. - [Score (vi)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Average Score | Result date | Report paper | | --- | --- | --- | --- | | BlueLM-V | 32.7 | Not recorded | 68fa75c31e209131cea69d07 | | InternVL2.5 | 31.9 | Not recorded | 68fa773a1e209131cea71d3c | | InternVL2.5-78B | 31.9 | Not recorded | 68fa7bab1e209131cea89c7f | | Qwen2.5-VL | 31.7 | Not recorded | 68fa773a1e209131cea71d3c | | InternVL2.5-38B | 31.7 | Not recorded | 68fa7bab1e209131cea89c7f | | Qwen2-VL | 30.9 | Not recorded | 68fa773a1e209131cea71d3c | | Qwen2-VL-72B | 30.9 | Not recorded | 68fa7bab1e209131cea89c7f | | Qwen2.5-VL | 29.2 | Not recorded | 68fa773a1e209131cea71d3c | | InternVL3.5-2B | 28.5 | Not recorded | 693115d7d6b0dd3342933d9a | | InternVL2.5-26B | 28.5 | Not recorded | 68fa7bab1e209131cea89c7f | | InternVL2.5-4B | 28.4 | Not recorded | 68fa7bab1e209131cea89c7f | | GPT-4o 0513 | 27.8 | Not recorded | 68fa773a1e209131cea71d3c | | GPT-4o | 27.8 | Not recorded | 68fa7bab1e209131cea89c7f | | InternVL2.5-8B | 27.6 | Not recorded | 68fa7bab1e209131cea89c7f | | Qwen3-VL-2B | 27.3 | Not recorded | 693115d7d6b0dd3342933d9a | | InternVL3-2B | 26.7 | Not recorded | 693115d7d6b0dd3342933d9a | | Claude-3.5 Sonnet-0620 | 25.7 | Not recorded | 68fa773a1e209131cea71d3c | | jina-vlm | 25.6 | Not recorded | 693115d7d6b0dd3342933d9a | | Qwen2-VL-7B | 25.6 | Not recorded | 68fa7bab1e209131cea89c7f | | Qwen2.5-VL | 24.8 | Not recorded | 68fa773a1e209131cea71d3c | | GPT-4V | 22 | Not recorded | 68fa7bab1e209131cea89c7f | | InternVL2-Llama3-76B | 22 | Not recorded | 68fa7bab1e209131cea89c7f | | InternVL2.5-2B | 21.8 | Not recorded | 68fa7bab1e209131cea89c7f | | InternVL2.5-1B | 21.4 | Not recorded | 68fa7bab1e209131cea89c7f | | InternVL2-8B | 20.9 | Not recorded | 68fa7bab1e209131cea89c7f | | Qwen2-VL | 20.7 | Not recorded | 68fa75c31e209131cea69d07 | | Qwen2-VL-2B | 20.6 | Not recorded | 693115d7d6b0dd3342933d9a | | InternVL2-40B | 20.6 | Not recorded | 68fa7bab1e209131cea89c7f | | InternVL-Chat-V1.5 | 20.5 | Not recorded | 68fa7bab1e209131cea89c7f | | Qwen2-VL-2B | 20 | Not recorded | 68fa7bab1e209131cea89c7f | | InternVL2-26B | 17.7 | Not recorded | 68fa7bab1e209131cea89c7f | | InternVL2 | 15.5 | Not recorded | 68fa75c31e209131cea69d07 | | InternVL2-4B | 15.3 | Not recorded | 68fa7bab1e209131cea89c7f | | Phi-3-Vision | 13.9 | Not recorded | 68fa75c31e209131cea69d07 | | InternVL2-1B | 12.6 | Not recorded | 68fa7bab1e209131cea89c7f | | InternVL2-2B | 10.9 | Not recorded | 68fa7bab1e209131cea89c7f | | MiniCPM-V-2 | 9.3 | Not recorded | 68fa75c31e209131cea69d07 | ### BlueLM-V Average Score: 32.7. Result ID: 6993fbb43a6c3148491a0efb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params":"3B"}. This record does not assert independent reproduction. ### InternVL2.5 Average Score: 31.9. Result ID: 69947b3b3a6c3148491d8300. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Number of Parameters":"78B"}. This record does not assert independent reproduction. ### InternVL2.5-78B Average Score: 31.9. Result ID: 69a1335f35dfcabb00e574e7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"78B"}. This record does not assert independent reproduction. ### Qwen2.5-VL Average Score: 31.7. Result ID: 69947b3b3a6c3148491d8302. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Parameters":"72B"}. This record does not assert independent reproduction. ### InternVL2.5-38B Average Score: 31.7. Result ID: 69a1335f35dfcabb00e574e2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"38B"}. This record does not assert independent reproduction. ### Qwen2-VL Average Score: 30.9. Result ID: 69947b3b3a6c3148491d8301. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Number of Parameters":"72B"}. This record does not assert independent reproduction. ### Qwen2-VL-72B Average Score: 30.9. Result ID: 69a1335f35dfcabb00e574e5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"72B"}. This record does not assert independent reproduction. ### Qwen2.5-VL Average Score: 29.2. Result ID: 69947b3b3a6c3148491d8303. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Parameters":"7B"}. This record does not assert independent reproduction. ### InternVL3.5-2B Average Score: 28.5. Result ID: 6996ce165698665ec41a0fb5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"parameters":"2B"}. This record does not assert independent reproduction. ### InternVL2.5-26B Average Score: 28.5. Result ID: 69a1335f35dfcabb00e574e0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"26B"}. This record does not assert independent reproduction. ### InternVL2.5-4B Average Score: 28.4. Result ID: 69a1335f35dfcabb00e574da. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"4B"}. This record does not assert independent reproduction. ### GPT-4o 0513 Average Score: 27.8. Result ID: 69947b3b3a6c3148491d82ff. [Reporting paper]() Recorded evaluation configuration: {"Model Version":"0513"}. This record does not assert independent reproduction. ### GPT-4o Average Score: 27.8. Result ID: 69a1335f35dfcabb00e574e4. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### InternVL2.5-8B Average Score: 27.6. Result ID: 69a1335f35dfcabb00e574dd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"8B"}. This record does not assert independent reproduction. ### Qwen3-VL-2B Average Score: 27.3. Result ID: 6996ce165698665ec41a0fb3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"parameters":"2B","evaluated\_by":"VLMEvalKit"}. This record does not assert independent reproduction. ### InternVL3-2B Average Score: 26.7. Result ID: 6996ce165698665ec41a0fb4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"parameters":"2B"}. This record does not assert independent reproduction. ### Claude-3.5 Sonnet-0620 Average Score: 25.7. Result ID: 69947b3b3a6c3148491d82fe. [Reporting paper]() Recorded evaluation configuration: {"Model Version":"0620"}. This record does not assert independent reproduction. ### jina-vlm Average Score: 25.6. Result ID: 6996ce165698665ec41a0fb1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen2-VL-7B Average Score: 25.6. Result ID: 69a1335f35dfcabb00e574db. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"7B"}. This record does not assert independent reproduction. ### Qwen2.5-VL Average Score: 24.8. Result ID: 69947b3b3a6c3148491d8304. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Parameters":"3B"}. This record does not assert independent reproduction. ### GPT-4V Average Score: 22. Result ID: 69a1335f35dfcabb00e574e3. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### InternVL2-Llama3-76B Average Score: 22. Result ID: 69a1335f35dfcabb00e574e6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Llama3","Parameters":"76B"}. This record does not assert independent reproduction. ### InternVL2.5-2B Average Score: 21.8. Result ID: 69a1335f35dfcabb00e574d8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"2B"}. This record does not assert independent reproduction. ### InternVL2.5-1B Average Score: 21.4. Result ID: 69a1335f35dfcabb00e574d5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"1B"}. This record does not assert independent reproduction. ### InternVL2-8B Average Score: 20.9. Result ID: 69a1335f35dfcabb00e574dc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"8B"}. This record does not assert independent reproduction. ### Qwen2-VL Average Score: 20.7. Result ID: 6993fbb43a6c3148491a0efa. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Params":"2B"}. This record does not assert independent reproduction. ### Qwen2-VL-2B Average Score: 20.6. Result ID: 6996ce165698665ec41a0fb2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"parameters":"2B"}. This record does not assert independent reproduction. ### InternVL2-40B Average Score: 20.6. Result ID: 69a1335f35dfcabb00e574e1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"40B"}. This record does not assert independent reproduction. ### InternVL-Chat-V1.5 Average Score: 20.5. Result ID: 69a1335f35dfcabb00e574de. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Version":"V1.5"}. This record does not assert independent reproduction. ### Qwen2-VL-2B Average Score: 20. Result ID: 69a1335f35dfcabb00e574d6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"2B"}. This record does not assert independent reproduction. ### InternVL2-26B Average Score: 17.7. Result ID: 69a1335f35dfcabb00e574df. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"26B"}. This record does not assert independent reproduction. ### InternVL2 Average Score: 15.5. Result ID: 6993fbb43a6c3148491a0ef9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Params":"4B"}. This record does not assert independent reproduction. ### InternVL2-4B Average Score: 15.3. Result ID: 69a1335f35dfcabb00e574d9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"4B"}. This record does not assert independent reproduction. ### Phi-3-Vision Average Score: 13.9. Result ID: 6993fbb43a6c3148491a0ef7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params":"4.2B"}. This record does not assert independent reproduction. ### InternVL2-1B Average Score: 12.6. Result ID: 69a1335f35dfcabb00e574d4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"1B"}. This record does not assert independent reproduction. ### InternVL2-2B Average Score: 10.9. Result ID: 69a1335f35dfcabb00e574d7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"2B"}. This record does not assert independent reproduction. ### MiniCPM-V-2 Average Score: 9.3. Result ID: 6993fbb43a6c3148491a0ef8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Params":"2.8B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.