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-007QWEN359B-004 Qwen3.5 9B SciCode Overall 27.7% Unknown Primary source QWEN-QWEN359B
BR-007QWEN359B-005 Qwen3.5 9B tau2-bench Overall 85.1% Unknown Primary source QWEN-QWEN359B
BR-007QWEN359B-006 Qwen3.5 9B tau3-Banking Overall 4.1% Unknown Primary source QWEN-QWEN359B
BR-007QWEN359B-007 Qwen3.5 9B Terminal-Bench Hard Overall 18.2% Unknown Primary source QWEN-QWEN359B
BR-007QWEN359B-008 Qwen3.5 9B Terminal-Bench 2.1 Overall 21.3% Unknown Primary source QWEN-QWEN359B
BR-007QWEN359B-009 Qwen3.5 9B CritPt Overall 0.6% Unknown Primary source QWEN-QWEN359B
BR-007QWEN359B-010 Qwen3.5 9B AA-Omniscience Overall -70.7 Unknown Primary source QWEN-QWEN359B
BR-007QWEN359B-011 Qwen3.5 9B AA-Omniscience Accuracy 14.1% Unknown Primary source QWEN-QWEN359B
BR-007QWEN359B-012 Qwen3.5 9B IFBench Overall 37.8% Unknown Primary source QWEN-QWEN359B
BR-007QWEN359B-013 Qwen3.5 9B MMMU-Pro Overall 66.8% Unknown Primary source QWEN-QWEN359B
BR-007QWEN359B-014 Qwen3.5 9B AA-LCR Overall 38% Unknown Primary source QWEN-QWEN359B
BR-007QWEN359B-015 Qwen3.5 9B Artificial Analysis Intelligence Index Overall 21.4 Unknown Primary source QWEN-QWEN359B
BR-007QWEN359B-016 Qwen3.5 9B GPQA Diamond Accuracy 80.6% Unknown Primary source QWEN-QWEN359B
BR-007QWEN359B-017 Qwen3.5 9B Humanity's Last Exam No tools Overall 13.3% Unknown Primary source QWEN-QWEN359B
BR-007QWEN359B-018 Qwen3.5 9B SciCode Overall 27.5% Unknown Primary source QWEN-QWEN359B
BR-007QWEN359B-019 Qwen3.5 9B tau2-bench Overall 86.8% Unknown Primary source QWEN-QWEN359B
BR-007QWEN359B-020 Qwen3.5 9B tau3-Banking Overall 8.2% Unknown Primary source QWEN-QWEN359B
BR-007QWEN359B-021 Qwen3.5 9B Terminal-Bench Hard Overall 24.2% Unknown Primary source QWEN-QWEN359B
BR-007QWEN359B-022 Qwen3.5 9B Terminal-Bench 2.1 Overall 29.2% Unknown Primary source QWEN-QWEN359B
BR-007QWEN359B-023 Qwen3.5 9B CritPt Overall 0.3% Unknown Primary source QWEN-QWEN359B
BR-007QWEN359B-024 Qwen3.5 9B AA-Omniscience Overall -52.5 Unknown Primary source QWEN-QWEN359B
BR-007QWEN359B-025 Qwen3.5 9B AA-Omniscience Accuracy 15.9% Unknown Primary source QWEN-QWEN359B
BR-007QWEN359B-026 Qwen3.5 9B IFBench Overall 66.7% Unknown Primary source QWEN-QWEN359B
BR-007QWEN359B-027 Qwen3.5 9B GDPval-AA Average Normalized Score 6.8% Unknown Primary source QWEN-QWEN359B
BR-007QWEN359B-028 Qwen3.5 9B MMMU-Pro Overall 69.2% Unknown Primary source QWEN-QWEN359B
BR-007QWEN359B-029 Qwen3.5 9B AA-LCR Overall 59% Unknown Primary source QWEN-QWEN359B
BR-007QWEN35OMNIFLASH-001 Qwen3.5 Omni Flash Artificial Analysis Intelligence Index Overall 19 Unknown Primary source QWEN-QWEN35OMNIFLASH
BR-007QWEN35OMNIFLASH-002 Qwen3.5 Omni Flash GPQA Diamond Accuracy 74.2% Unknown Primary source QWEN-QWEN35OMNIFLASH
BR-007QWEN35OMNIFLASH-003 Qwen3.5 Omni Flash Humanity's Last Exam No tools Overall 7.1% Unknown Primary source QWEN-QWEN35OMNIFLASH
BR-007QWEN35OMNIFLASH-004 Qwen3.5 Omni Flash SciCode Overall 25.5% Unknown Primary source QWEN-QWEN35OMNIFLASH
BR-007QWEN35OMNIFLASH-005 Qwen3.5 Omni Flash tau2-bench Overall 84.5% Unknown Primary source QWEN-QWEN35OMNIFLASH
BR-007QWEN35OMNIFLASH-006 Qwen3.5 Omni Flash Terminal-Bench Hard Overall 8.3% Unknown Primary source QWEN-QWEN35OMNIFLASH
BR-007QWEN35OMNIFLASH-007 Qwen3.5 Omni Flash CritPt Overall 0% Unknown Primary source QWEN-QWEN35OMNIFLASH
BR-007QWEN35OMNIFLASH-008 Qwen3.5 Omni Flash AA-Omniscience Overall -65.6 Unknown Primary source QWEN-QWEN35OMNIFLASH
BR-007QWEN35OMNIFLASH-009 Qwen3.5 Omni Flash AA-Omniscience Accuracy 14.5% Unknown Primary source QWEN-QWEN35OMNIFLASH
BR-007QWEN35OMNIFLASH-010 Qwen3.5 Omni Flash IFBench Overall 38% Unknown Primary source QWEN-QWEN35OMNIFLASH
BR-007QWEN35OMNIFLASH-011 Qwen3.5 Omni Flash MMMU-Pro Overall 64.7% Unknown Primary source QWEN-QWEN35OMNIFLASH
BR-007QWEN35OMNIFLASH-012 Qwen3.5 Omni Flash AA-LCR Overall 44% Unknown Primary source QWEN-QWEN35OMNIFLASH
BR-007QWEN35OMNIPLUS-001 Qwen3.5 Omni Plus Artificial Analysis Intelligence Index Overall 30.6 Unknown Primary source QWEN-QWEN35OMNIPLUS
BR-007QWEN35OMNIPLUS-002 Qwen3.5 Omni Plus GPQA Diamond Accuracy 82.6% Unknown Primary source QWEN-QWEN35OMNIPLUS
BR-007QWEN35OMNIPLUS-003 Qwen3.5 Omni Plus Humanity's Last Exam No tools Overall 13.9% Unknown Primary source QWEN-QWEN35OMNIPLUS
BR-007QWEN35OMNIPLUS-004 Qwen3.5 Omni Plus SciCode Overall 40.5% Unknown Primary source QWEN-QWEN35OMNIPLUS
BR-007QWEN35OMNIPLUS-005 Qwen3.5 Omni Plus tau2-bench Overall 88.3% Unknown Primary source QWEN-QWEN35OMNIPLUS
BR-007QWEN35OMNIPLUS-006 Qwen3.5 Omni Plus Terminal-Bench Hard Overall 21.2% Unknown Primary source QWEN-QWEN35OMNIPLUS
BR-007QWEN35OMNIPLUS-007 Qwen3.5 Omni Plus CritPt Overall 0.6% Unknown Primary source QWEN-QWEN35OMNIPLUS
BR-007QWEN35OMNIPLUS-008 Qwen3.5 Omni Plus AA-Omniscience Overall -12.3 Unknown Primary source QWEN-QWEN35OMNIPLUS
BR-007QWEN35OMNIPLUS-009 Qwen3.5 Omni Plus AA-Omniscience Accuracy 17.4% Unknown Primary source QWEN-QWEN35OMNIPLUS
BR-007QWEN35OMNIPLUS-010 Qwen3.5 Omni Plus IFBench Overall 51.2% Unknown Primary source QWEN-QWEN35OMNIPLUS
BR-007QWEN35OMNIPLUS-011 Qwen3.5 Omni Plus MMMU-Pro Overall 70.5% Unknown Primary source QWEN-QWEN35OMNIPLUS
BR-007QWEN35OMNIPLUS-012 Qwen3.5 Omni Plus AA-LCR Overall 52.7% Unknown Primary source QWEN-QWEN35OMNIPLUS
BR-007QWEN3627B-001 Qwen3.6 27B Artificial Analysis Intelligence Index Overall 30.5 Unknown Primary source QWEN-QWEN3627B
BR-007QWEN3627B-002 Qwen3.6 27B GPQA Diamond Accuracy 82.9% Unknown Primary source QWEN-QWEN3627B
BR-007QWEN3627B-003 Qwen3.6 27B Humanity's Last Exam No tools Overall 13.6% Unknown Primary source QWEN-QWEN3627B
BR-007QWEN3627B-004 Qwen3.6 27B SciCode Overall 37.3% Unknown Primary source QWEN-QWEN3627B
BR-007QWEN3627B-005 Qwen3.6 27B tau2-bench Overall 93.6% Unknown Primary source QWEN-QWEN3627B
BR-007QWEN3627B-006 Qwen3.6 27B tau3-Banking Overall 8.2% Unknown Primary source QWEN-QWEN3627B
BR-007QWEN3627B-007 Qwen3.6 27B Terminal-Bench Hard Overall 21.2% Unknown Primary source QWEN-QWEN3627B
BR-007QWEN3627B-008 Qwen3.6 27B Terminal-Bench 2.1 Overall 51.3% Unknown Primary source QWEN-QWEN3627B
BR-007QWEN3627B-009 Qwen3.6 27B CritPt Overall 0.9% Unknown Primary source QWEN-QWEN3627B
BR-007QWEN3627B-010 Qwen3.6 27B AA-Omniscience Overall -52.8 Unknown Primary source QWEN-QWEN3627B
BR-007QWEN3627B-011 Qwen3.6 27B AA-Omniscience Accuracy 17% Unknown Primary source QWEN-QWEN3627B
BR-007QWEN3627B-012 Qwen3.6 27B IFBench Overall 45.7% Unknown Primary source QWEN-QWEN3627B
BR-007QWEN3627B-013 Qwen3.6 27B GDPval-AA Average Normalized Score 30.6% Unknown Primary source QWEN-QWEN3627B
BR-007QWEN3627B-014 Qwen3.6 27B MMMU-Pro Overall 71.7% Unknown Primary source QWEN-QWEN3627B
BR-007QWEN3627B-015 Qwen3.6 27B AA-LCR Overall 55% Unknown Primary source QWEN-QWEN3627B
BR-007QWEN3627B-016 Qwen3.6 27B Artificial Analysis Intelligence Index Overall 37.1 Unknown Primary source QWEN-QWEN3627B
BR-007QWEN3627B-017 Qwen3.6 27B GPQA Diamond Accuracy 84.2% Unknown Primary source QWEN-QWEN3627B
BR-007QWEN3627B-018 Qwen3.6 27B Humanity's Last Exam No tools Overall 21.6% Unknown Primary source QWEN-QWEN3627B
BR-007QWEN3627B-019 Qwen3.6 27B SciCode Overall 39.8% Unknown Primary source QWEN-QWEN3627B
BR-007QWEN3627B-020 Qwen3.6 27B tau2-bench Overall 94.2% Unknown Primary source QWEN-QWEN3627B
BR-007QWEN3627B-021 Qwen3.6 27B tau3-Banking Overall 15.3% Unknown Primary source QWEN-QWEN3627B
BR-007QWEN3627B-022 Qwen3.6 27B Terminal-Bench Hard Overall 34.8% Unknown Primary source QWEN-QWEN3627B
BR-007QWEN3627B-023 Qwen3.6 27B Terminal-Bench 2.1 Overall 60.7% Unknown Primary source QWEN-QWEN3627B
BR-007QWEN3627B-024 Qwen3.6 27B CritPt Overall 1.1% Unknown Primary source QWEN-QWEN3627B
BR-007QWEN3627B-025 Qwen3.6 27B AA-Omniscience Overall -19.8 Unknown Primary source QWEN-QWEN3627B
BR-007QWEN3627B-026 Qwen3.6 27B AA-Omniscience Accuracy 19.2% Unknown Primary source QWEN-QWEN3627B
BR-007QWEN3627B-027 Qwen3.6 27B IFBench Overall 67.6% Unknown Primary source QWEN-QWEN3627B
BR-007QWEN3627B-028 Qwen3.6 27B GDPval-AA Average Normalized Score 32% Unknown Primary source QWEN-QWEN3627B
BR-007QWEN3627B-029 Qwen3.6 27B MMMU-Pro Overall 74.6% Unknown Primary source QWEN-QWEN3627B
BR-007QWEN3627B-030 Qwen3.6 27B AA-LCR Overall 68.7% Unknown Primary source QWEN-QWEN3627B
BR-007QWEN3635BA3B-001 Qwen3.6 35B A3B Artificial Analysis Intelligence Index Overall 24.2 Unknown Primary source QWEN-QWEN3635BA3B
BR-007QWEN3635BA3B-002 Qwen3.6 35B A3B GPQA Diamond Accuracy 81.7% Unknown Primary source QWEN-QWEN3635BA3B
BR-007QWEN3635BA3B-003 Qwen3.6 35B A3B Humanity's Last Exam No tools Overall 12.5% Unknown Primary source QWEN-QWEN3635BA3B
BR-007QWEN3635BA3B-004 Qwen3.6 35B A3B SciCode Overall 1.3% Unknown Primary source QWEN-QWEN3635BA3B
BR-007QWEN3635BA3B-005 Qwen3.6 35B A3B tau2-bench Overall 85.1% Unknown Primary source QWEN-QWEN3635BA3B
BR-007QWEN3635BA3B-006 Qwen3.6 35B A3B Terminal-Bench Hard Overall 25.8% Unknown Primary source QWEN-QWEN3635BA3B
BR-007QWEN3635BA3B-007 Qwen3.6 35B A3B CritPt Overall 0% Unknown Primary source QWEN-QWEN3635BA3B
BR-007QWEN3635BA3B-008 Qwen3.6 35B A3B AA-Omniscience Overall -59.8 Unknown Primary source QWEN-QWEN3635BA3B
BR-007QWEN3635BA3B-009 Qwen3.6 35B A3B AA-Omniscience Accuracy 17.1% Unknown Primary source QWEN-QWEN3635BA3B
BR-007QWEN3635BA3B-010 Qwen3.6 35B A3B IFBench Overall 36.2% Unknown Primary source QWEN-QWEN3635BA3B
BR-007QWEN3635BA3B-011 Qwen3.6 35B A3B GDPval-AA Average Normalized Score 26.1% Unknown Primary source QWEN-QWEN3635BA3B
BR-007QWEN3635BA3B-012 Qwen3.6 35B A3B MMMU-Pro Overall 71% Unknown Primary source QWEN-QWEN3635BA3B
BR-007QWEN3635BA3B-013 Qwen3.6 35B A3B AA-LCR Overall 56.7% Unknown Primary source QWEN-QWEN3635BA3B
BR-007QWEN3635BA3B-014 Qwen3.6 35B A3B Artificial Analysis Intelligence Index Overall 31.6 Unknown Primary source QWEN-QWEN3635BA3B
BR-007QWEN3635BA3B-015 Qwen3.6 35B A3B GPQA Diamond Accuracy 84.1% Unknown Primary source QWEN-QWEN3635BA3B
BR-007QWEN3635BA3B-016 Qwen3.6 35B A3B Humanity's Last Exam No tools Overall 20.2% Unknown Primary source QWEN-QWEN3635BA3B
BR-007QWEN3635BA3B-017 Qwen3.6 35B A3B SciCode Overall 35.8% Unknown Primary source QWEN-QWEN3635BA3B
BR-007QWEN3635BA3B-018 Qwen3.6 35B A3B tau2-bench Overall 95.3% Unknown Primary source QWEN-QWEN3635BA3B
BR-007QWEN3635BA3B-019 Qwen3.6 35B A3B tau3-Banking Overall 8.7% Unknown Primary source QWEN-QWEN3635BA3B
BR-007QWEN3635BA3B-020 Qwen3.6 35B A3B Terminal-Bench Hard Overall 34.8% Unknown Primary source QWEN-QWEN3635BA3B