BENCHMARK REGISTRY
Public Artificial Intelligence Benchmark Records Database
Search operators

brand: benchmark: record: model: metric: date: org:

Separate values with commas, or alternatives with uppercase OR. Example: brand:Meta, Anthropic benchmark:GPQA

Qwen

Provider prefix
QWEN
Benchmark Record namespace
007

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-007QWEN3VL4B-009 Qwen3 VL 4B AA-Omniscience Accuracy 12.2% Unknown Primary source QWEN-QWEN3VL4B
BR-007QWEN3VL4B-010 Qwen3 VL 4B IFBench Overall 36.6% Unknown Primary source QWEN-QWEN3VL4B
BR-007QWEN3VL4B-011 Qwen3 VL 4B MMMU-Pro Overall 52% Unknown Primary source QWEN-QWEN3VL4B
BR-007QWEN3VL4B-012 Qwen3 VL 4B AA-LCR Overall 21.3% Unknown Primary source QWEN-QWEN3VL4B
BR-007QWEN3VL4BINSTRUCT-001 Qwen3 VL 4B Instruct Artificial Analysis Intelligence Index Overall 4.1 Unknown Primary source QWEN-QWEN3VL4BINSTRUCT
BR-007QWEN3VL4BINSTRUCT-002 Qwen3 VL 4B Instruct GPQA Diamond Accuracy 37.1% Unknown Primary source QWEN-QWEN3VL4BINSTRUCT
BR-007QWEN3VL4BINSTRUCT-003 Qwen3 VL 4B Instruct Humanity's Last Exam No tools Overall 3.7% Unknown Primary source QWEN-QWEN3VL4BINSTRUCT
BR-007QWEN3VL4BINSTRUCT-004 Qwen3 VL 4B Instruct SciCode Overall 13.7% Unknown Primary source QWEN-QWEN3VL4BINSTRUCT
BR-007QWEN3VL4BINSTRUCT-005 Qwen3 VL 4B Instruct tau2-bench Overall 23.4% Unknown Primary source QWEN-QWEN3VL4BINSTRUCT
BR-007QWEN3VL4BINSTRUCT-006 Qwen3 VL 4B Instruct Terminal-Bench Hard Overall 0% Unknown Primary source QWEN-QWEN3VL4BINSTRUCT
BR-007QWEN3VL4BINSTRUCT-007 Qwen3 VL 4B Instruct CritPt Overall 0% Unknown Primary source QWEN-QWEN3VL4BINSTRUCT
BR-007QWEN3VL4BINSTRUCT-008 Qwen3 VL 4B Instruct AA-Omniscience Overall -75.8 Unknown Primary source QWEN-QWEN3VL4BINSTRUCT
BR-007QWEN3VL4BINSTRUCT-009 Qwen3 VL 4B Instruct AA-Omniscience Accuracy 10.4% Unknown Primary source QWEN-QWEN3VL4BINSTRUCT
BR-007QWEN3VL4BINSTRUCT-010 Qwen3 VL 4B Instruct IFBench Overall 31.8% Unknown Primary source QWEN-QWEN3VL4BINSTRUCT
BR-007QWEN3VL4BINSTRUCT-011 Qwen3 VL 4B Instruct MMMU-Pro Overall 43.9% Unknown Primary source QWEN-QWEN3VL4BINSTRUCT
BR-007QWEN3VL4BINSTRUCT-012 Qwen3 VL 4B Instruct AA-LCR Overall 13% Unknown Primary source QWEN-QWEN3VL4BINSTRUCT
BR-007QWEN3VL8B-001 Qwen3 VL 8B Artificial Analysis Intelligence Index Overall 10.6 Unknown Primary source QWEN-QWEN3VL8B
BR-007QWEN3VL8B-002 Qwen3 VL 8B GPQA Diamond Accuracy 57.9% Unknown Primary source QWEN-QWEN3VL8B
BR-007QWEN3VL8B-003 Qwen3 VL 8B Humanity's Last Exam No tools Overall 3.3% Unknown Primary source QWEN-QWEN3VL8B
BR-007QWEN3VL8B-004 Qwen3 VL 8B SciCode Overall 21.9% Unknown Primary source QWEN-QWEN3VL8B
BR-007QWEN3VL8B-005 Qwen3 VL 8B tau2-bench Overall 22.5% Unknown Primary source QWEN-QWEN3VL8B
BR-007QWEN3VL8B-006 Qwen3 VL 8B Terminal-Bench Hard Overall 3.8% Unknown Primary source QWEN-QWEN3VL8B
BR-007QWEN3VL8B-007 Qwen3 VL 8B CritPt Overall 0.3% Unknown Primary source QWEN-QWEN3VL8B
BR-007QWEN3VL8B-008 Qwen3 VL 8B AA-Omniscience Overall -52.4 Unknown Primary source QWEN-QWEN3VL8B
BR-007QWEN3VL8B-009 Qwen3 VL 8B AA-Omniscience Accuracy 20.1% Unknown Primary source QWEN-QWEN3VL8B
BR-007QWEN3VL8B-010 Qwen3 VL 8B IFBench Overall 39.9% Unknown Primary source QWEN-QWEN3VL8B
BR-007QWEN3VL8B-011 Qwen3 VL 8B MMMU-Pro Overall 56.6% Unknown Primary source QWEN-QWEN3VL8B
BR-007QWEN3VL8B-012 Qwen3 VL 8B AA-LCR Overall 31% Unknown Primary source QWEN-QWEN3VL8B
BR-007QWEN3VL8BINSTRUCT-001 Qwen3 VL 8B Instruct Artificial Analysis Intelligence Index Overall 8.4 Unknown Primary source QWEN-QWEN3VL8BINSTRUCT
BR-007QWEN3VL8BINSTRUCT-002 Qwen3 VL 8B Instruct GPQA Diamond Accuracy 42.7% Unknown Primary source QWEN-QWEN3VL8BINSTRUCT
BR-007QWEN3VL8BINSTRUCT-003 Qwen3 VL 8B Instruct Humanity's Last Exam No tools Overall 2.9% Unknown Primary source QWEN-QWEN3VL8BINSTRUCT
BR-007QWEN3VL8BINSTRUCT-004 Qwen3 VL 8B Instruct SciCode Overall 17.4% Unknown Primary source QWEN-QWEN3VL8BINSTRUCT
BR-007QWEN3VL8BINSTRUCT-005 Qwen3 VL 8B Instruct tau2-bench Overall 29.2% Unknown Primary source QWEN-QWEN3VL8BINSTRUCT
BR-007QWEN3VL8BINSTRUCT-006 Qwen3 VL 8B Instruct Terminal-Bench Hard Overall 2.3% Unknown Primary source QWEN-QWEN3VL8BINSTRUCT
BR-007QWEN3VL8BINSTRUCT-007 Qwen3 VL 8B Instruct CritPt Overall 0% Unknown Primary source QWEN-QWEN3VL8BINSTRUCT
BR-007QWEN3VL8BINSTRUCT-008 Qwen3 VL 8B Instruct AA-Omniscience Overall -52 Unknown Primary source QWEN-QWEN3VL8BINSTRUCT
BR-007QWEN3VL8BINSTRUCT-009 Qwen3 VL 8B Instruct AA-Omniscience Accuracy 20.2% Unknown Primary source QWEN-QWEN3VL8BINSTRUCT
BR-007QWEN3VL8BINSTRUCT-010 Qwen3 VL 8B Instruct IFBench Overall 32.3% Unknown Primary source QWEN-QWEN3VL8BINSTRUCT
BR-007QWEN3VL8BINSTRUCT-011 Qwen3 VL 8B Instruct MMMU-Pro Overall 47.3% Unknown Primary source QWEN-QWEN3VL8BINSTRUCT
BR-007QWEN3VL8BINSTRUCT-012 Qwen3 VL 8B Instruct AA-LCR Overall 15.3% Unknown Primary source QWEN-QWEN3VL8BINSTRUCT
BR-007QWENCHAT14B-001 Qwen Chat 14B Artificial Analysis Intelligence Index Overall 2.1 Unknown Primary source QWEN-QWENCHAT14B
BR-007QWENCHAT72B-001 Qwen Chat 72B Artificial Analysis Intelligence Index Overall 3.4 Unknown Primary source QWEN-QWENCHAT72B
BR-007QWQ32B-001 QwQ 32B Artificial Analysis Intelligence Index Overall 13.4 Unknown Primary source QWEN-QWQ32B
BR-007QWQ32B-002 QwQ 32B GPQA Diamond Accuracy 59.3% Unknown Primary source QWEN-QWQ32B
BR-007QWQ32B-003 QwQ 32B Humanity's Last Exam No tools Overall 8.2% Unknown Primary source QWEN-QWQ32B
BR-007QWQ32B-004 QwQ 32B SciCode Overall 35.8% Unknown Primary source QWEN-QWQ32B
BR-007QWQ32B-005 QwQ 32B IFBench Overall 38.8% Unknown Primary source QWEN-QWQ32B
BR-007QWQ32B-006 QwQ 32B AA-LCR Overall 25% Unknown Primary source QWEN-QWQ32B
BR-007QWQ32BPREVIEW-001 QwQ 32B-Preview Artificial Analysis Intelligence Index Overall 9.2 Unknown Primary source QWEN-QWQ32BPREVIEW
BR-007QWQ32BPREVIEW-002 QwQ 32B-Preview GPQA Diamond Accuracy 55.7% Unknown Primary source QWEN-QWQ32BPREVIEW
BR-007QWQ32BPREVIEW-003 QwQ 32B-Preview Humanity's Last Exam No tools Overall 4.8% Unknown Primary source QWEN-QWQ32BPREVIEW
BR-007QWQ32BPREVIEW-004 QwQ 32B-Preview SciCode Overall 3.8% Unknown Primary source QWEN-QWQ32BPREVIEW