Baidu

Provider prefix
BAIDU
Benchmark Record namespace
036

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-036ERNIE45300BA47B-001 ERNIE 4.5 300B A47B Artificial Analysis Intelligence Index Overall 9 Unknown Primary source BAIDU-ERNIE45300BA47B
BR-036ERNIE45300BA47B-002 ERNIE 4.5 300B A47B GPQA Diamond Accuracy 81.1% Unknown Primary source BAIDU-ERNIE45300BA47B
BR-036ERNIE45300BA47B-003 ERNIE 4.5 300B A47B Humanity's Last Exam No tools Overall 3.5% Unknown Primary source BAIDU-ERNIE45300BA47B
BR-036ERNIE45300BA47B-004 ERNIE 4.5 300B A47B SciCode Overall 31.5% Unknown Primary source BAIDU-ERNIE45300BA47B
BR-036ERNIE45300BA47B-005 ERNIE 4.5 300B A47B tau2-bench Overall 0% Unknown Primary source BAIDU-ERNIE45300BA47B
BR-036ERNIE45300BA47B-006 ERNIE 4.5 300B A47B Terminal-Bench Hard Overall 6.1% Unknown Primary source BAIDU-ERNIE45300BA47B
BR-036ERNIE45300BA47B-007 ERNIE 4.5 300B A47B CritPt Overall 0% Unknown Primary source BAIDU-ERNIE45300BA47B
BR-036ERNIE45300BA47B-008 ERNIE 4.5 300B A47B AA-Omniscience Overall -35.9 Unknown Primary source BAIDU-ERNIE45300BA47B
BR-036ERNIE45300BA47B-009 ERNIE 4.5 300B A47B AA-Omniscience Accuracy 18.7% Unknown Primary source BAIDU-ERNIE45300BA47B
BR-036ERNIE45300BA47B-010 ERNIE 4.5 300B A47B IFBench Overall 39.1% Unknown Primary source BAIDU-ERNIE45300BA47B
BR-036ERNIE45300BA47B-011 ERNIE 4.5 300B A47B AA-LCR Overall 2.3% Unknown Primary source BAIDU-ERNIE45300BA47B
BR-036ERNIE50THINKINGPREVIEW-001 ERNIE 5.0 Thinking Preview Artificial Analysis Intelligence Index Overall 21.9 Unknown Primary source BAIDU-ERNIE50THINKINGPREVIEW
BR-036ERNIE50THINKINGPREVIEW-002 ERNIE 5.0 Thinking Preview GPQA Diamond Accuracy 77.7% Unknown Primary source BAIDU-ERNIE50THINKINGPREVIEW
BR-036ERNIE50THINKINGPREVIEW-003 ERNIE 5.0 Thinking Preview Humanity's Last Exam No tools Overall 12.7% Unknown Primary source BAIDU-ERNIE50THINKINGPREVIEW
BR-036ERNIE50THINKINGPREVIEW-004 ERNIE 5.0 Thinking Preview SciCode Overall 37.5% Unknown Primary source BAIDU-ERNIE50THINKINGPREVIEW
BR-036ERNIE50THINKINGPREVIEW-005 ERNIE 5.0 Thinking Preview tau2-bench Overall 83.9% Unknown Primary source BAIDU-ERNIE50THINKINGPREVIEW
BR-036ERNIE50THINKINGPREVIEW-006 ERNIE 5.0 Thinking Preview Terminal-Bench Hard Overall 25% Unknown Primary source BAIDU-ERNIE50THINKINGPREVIEW
BR-036ERNIE50THINKINGPREVIEW-007 ERNIE 5.0 Thinking Preview CritPt Overall 1.4% Unknown Primary source BAIDU-ERNIE50THINKINGPREVIEW
BR-036ERNIE50THINKINGPREVIEW-008 ERNIE 5.0 Thinking Preview AA-Omniscience Overall -44.1 Unknown Primary source BAIDU-ERNIE50THINKINGPREVIEW
BR-036ERNIE50THINKINGPREVIEW-009 ERNIE 5.0 Thinking Preview AA-Omniscience Accuracy 21.9% Unknown Primary source BAIDU-ERNIE50THINKINGPREVIEW
BR-036ERNIE50THINKINGPREVIEW-010 ERNIE 5.0 Thinking Preview IFBench Overall 41.4% Unknown Primary source BAIDU-ERNIE50THINKINGPREVIEW
BR-036ERNIE50THINKINGPREVIEW-011 ERNIE 5.0 Thinking Preview MMMU-Pro Overall 64.6% Unknown Primary source BAIDU-ERNIE50THINKINGPREVIEW
BR-036ERNIE50THINKINGPREVIEW-012 ERNIE 5.0 Thinking Preview AA-LCR Overall 6.7% Unknown Primary source BAIDU-ERNIE50THINKINGPREVIEW