# Chinese Language Understanding on CLUEWSC Source: [Chinese Language Understanding on CLUEWSC]() Collection index: [llms.txt]() Data updated: 2026-06-25T07:48:12.018Z Evaluation of model performance on the CLUEWSC dataset focusing on Chinese Language Understanding tasks, measured by Exact Match (EM). 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 | Chinese Language Understanding | | Dataset (including any stated split) | CLUEWSC | | Metric | Exact Match (EM) | | 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 - [Exact Match (EM)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Exact Match (EM) | Result date | Report paper | | --- | --- | --- | --- | | Opus-4.6 | 95.8 | Not recorded | 6a3cb602206542251d7ca4df | | Qwen3.5-Plus | 95.6 | Not recorded | 6a3cb602206542251d7ca4df | | GPT-5.4 | 95.1 | Not recorded | 6a3cb602206542251d7ca4df | | Qwen3-VL-32B | 94.9 | Not recorded | 6a3cb602206542251d7ca4df | | Qwen3-VL-32B | 94.6 | Not recorded | 6a3cb602206542251d7ca4df | | Yuvion VL-32B | 93.3 | Not recorded | 6a3cb602206542251d7ca4df | | DeepSeek-R1 | 92.8 | Not recorded | 68fa76a91e209131cea6e3eb | | K2.5 | 92.8 | Not recorded | 6a3cb602206542251d7ca4df | | Yuvion VL-32B | 92.7 | Not recorded | 6a3cb602206542251d7ca4df | | Qwen3-VL-8B | 92 | Not recorded | 6a3cb602206542251d7ca4df | | Qwen3-VL-8B | 91.6 | Not recorded | 6a3cb602206542251d7ca4df | | Yuvion VL-8B | 91.1 | Not recorded | 6a3cb602206542251d7ca4df | | DeepSeek-V3 | 90.9 | Not recorded | 68fa76a91e209131cea6e3eb | | OpenAI-o1-mini | 89.9 | Not recorded | 68fa76a91e209131cea6e3eb | | Yuvion VL-8B | 88.3 | Not recorded | 6a3cb602206542251d7ca4df | | GPT-4o-0513 | 87.9 | Not recorded | 68fa76a91e209131cea6e3eb | | Claude-3.5-Sonnet-1022 | 85.4 | Not recorded | 68fa76a91e209131cea6e3eb | ### Opus-4.6 Exact Match (EM): 95.8. Result ID: 6a3cdd28fbc373592c51ad17. [Reporting paper]() Recorded evaluation configuration: {"Parameter Count":"≈800B"}. This record does not assert independent reproduction. ### Qwen3.5-Plus Exact Match (EM): 95.6. Result ID: 6a3cdd28fbc373592c51ad19. [Reporting paper]() Recorded evaluation configuration: {"Parameter Count":"397B"}. This record does not assert independent reproduction. ### GPT-5.4 Exact Match (EM): 95.1. Result ID: 6a3cdd28fbc373592c51ad16. [Reporting paper]() Recorded evaluation configuration: {"Parameter Count":"≈1.5T"}. This record does not assert independent reproduction. ### Qwen3-VL-32B Exact Match (EM): 94.9. Result ID: 6a3cdd28fbc373592c51ad13. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Decoding Mode":"Thinking","Model Scale":"32B"}. This record does not assert independent reproduction. ### Qwen3-VL-32B Exact Match (EM): 94.6. Result ID: 6a3cdd28fbc373592c51ad12. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Decoding Mode":"Instruct","Model Scale":"32B"}. This record does not assert independent reproduction. ### Yuvion VL-32B Exact Match (EM): 93.3. Result ID: 6a3cdd28fbc373592c51ad15. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Decoding Mode":"Reasoning","Model Scale":"32B"}. This record does not assert independent reproduction. ### DeepSeek-R1 Exact Match (EM): 92.8. Result ID: 69945c4a3a6c3148491cbe3f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"MoE","Activated Params":"37B","Total Params":"671B"}. This record does not assert independent reproduction. ### K2.5 Exact Match (EM): 92.8. Result ID: 6a3cdd28fbc373592c51ad18. [Reporting paper]() Recorded evaluation configuration: {"Parameter Count":"≈1T"}. This record does not assert independent reproduction. ### Yuvion VL-32B Exact Match (EM): 92.7. Result ID: 6a3cdd28fbc373592c51ad14. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Decoding Mode":"Instruct","Model Scale":"32B"}. This record does not assert independent reproduction. ### Qwen3-VL-8B Exact Match (EM): 92. Result ID: 6a3cdd28fbc373592c51ad0f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Decoding Mode":"Thinking","Model Scale":"8B"}. This record does not assert independent reproduction. ### Qwen3-VL-8B Exact Match (EM): 91.6. Result ID: 6a3cdd28fbc373592c51ad0e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Decoding Mode":"Instruct","Model Scale":"8B"}. This record does not assert independent reproduction. ### Yuvion VL-8B Exact Match (EM): 91.1. Result ID: 6a3cdd28fbc373592c51ad11. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Decoding Mode":"Reasoning","Model Scale":"8B"}. This record does not assert independent reproduction. ### DeepSeek-V3 Exact Match (EM): 90.9. Result ID: 69945c4a3a6c3148491cbe3d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"MoE","Activated Params":"37B","Total Params":"671B"}. This record does not assert independent reproduction. ### OpenAI-o1-mini Exact Match (EM): 89.9. Result ID: 69945c4a3a6c3148491cbe3e. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Yuvion VL-8B Exact Match (EM): 88.3. Result ID: 6a3cdd28fbc373592c51ad10. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Decoding Mode":"Instruct","Model Scale":"8B"}. This record does not assert independent reproduction. ### GPT-4o-0513 Exact Match (EM): 87.9. Result ID: 69945c4a3a6c3148491cbe3c. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Claude-3.5-Sonnet-1022 Exact Match (EM): 85.4. Result ID: 69945c4a3a6c3148491cbe3b. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.