BENCHMARK REGISTRY
Public Artificial Intelligence Benchmark Records Database

IBM

Provider prefix
IBM
Benchmark Record namespace
017

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-017GRANITE338B-001 Granite 3.3 8B Artificial Analysis Intelligence Index Overall 1.8 Unknown Primary source IBM-GRANITE338B
BR-017GRANITE338B-002 Granite 3.3 8B GPQA Diamond Accuracy 33.8% Unknown Primary source IBM-GRANITE338B
BR-017GRANITE338B-003 Granite 3.3 8B Humanity's Last Exam No tools Overall 4.2% Unknown Primary source IBM-GRANITE338B
BR-017GRANITE338B-004 Granite 3.3 8B SciCode Overall 10.1% Unknown Primary source IBM-GRANITE338B
BR-017GRANITE338B-005 Granite 3.3 8B tau2-bench Overall 10.5% Unknown Primary source IBM-GRANITE338B
BR-017GRANITE338B-006 Granite 3.3 8B Terminal-Bench Hard Overall 0% Unknown Primary source IBM-GRANITE338B
BR-017GRANITE338B-007 Granite 3.3 8B CritPt Overall 0% Unknown Primary source IBM-GRANITE338B
BR-017GRANITE338B-008 Granite 3.3 8B AA-Omniscience Overall -76.6 Unknown Primary source IBM-GRANITE338B
BR-017GRANITE338B-009 Granite 3.3 8B AA-Omniscience Accuracy 8.5% Unknown Primary source IBM-GRANITE338B
BR-017GRANITE338B-010 Granite 3.3 8B IFBench Overall 22.4% Unknown Primary source IBM-GRANITE338B
BR-017GRANITE338B-011 Granite 3.3 8B AA-LCR Overall 4.3% Unknown Primary source IBM-GRANITE338B
BR-017GRANITE401B-001 Granite 4.0 1B Artificial Analysis Intelligence Index Overall 2.1 Unknown Primary source IBM-GRANITE401B
BR-017GRANITE401B-002 Granite 4.0 1B GPQA Diamond Accuracy 28.1% Unknown Primary source IBM-GRANITE401B
BR-017GRANITE401B-003 Granite 4.0 1B Humanity's Last Exam No tools Overall 5.1% Unknown Primary source IBM-GRANITE401B
BR-017GRANITE401B-004 Granite 4.0 1B SciCode Overall 8.7% Unknown Primary source IBM-GRANITE401B
BR-017GRANITE401B-005 Granite 4.0 1B tau2-bench Overall 22.8% Unknown Primary source IBM-GRANITE401B
BR-017GRANITE401B-006 Granite 4.0 1B Terminal-Bench Hard Overall 0% Unknown Primary source IBM-GRANITE401B
BR-017GRANITE401B-007 Granite 4.0 1B CritPt Overall 0% Unknown Primary source IBM-GRANITE401B
BR-017GRANITE401B-008 Granite 4.0 1B AA-Omniscience Overall -81.8 Unknown Primary source IBM-GRANITE401B
BR-017GRANITE401B-009 Granite 4.0 1B AA-Omniscience Accuracy 6.1% Unknown Primary source IBM-GRANITE401B
BR-017GRANITE401B-010 Granite 4.0 1B IFBench Overall 20.5% Unknown Primary source IBM-GRANITE401B
BR-017GRANITE401B-011 Granite 4.0 1B AA-LCR Overall 4% Unknown Primary source IBM-GRANITE401B
BR-017GRANITE40350M-001 Granite 4.0 350M Artificial Analysis Intelligence Index Overall 1 Unknown Primary source IBM-GRANITE40350M
BR-017GRANITE40350M-002 Granite 4.0 350M GPQA Diamond Accuracy 26.1% Unknown Primary source IBM-GRANITE40350M
BR-017GRANITE40350M-003 Granite 4.0 350M Humanity's Last Exam No tools Overall 5.7% Unknown Primary source IBM-GRANITE40350M
BR-017GRANITE40350M-004 Granite 4.0 350M SciCode Overall 0.9% Unknown Primary source IBM-GRANITE40350M
BR-017GRANITE40350M-005 Granite 4.0 350M tau2-bench Overall 13.2% Unknown Primary source IBM-GRANITE40350M
BR-017GRANITE40350M-006 Granite 4.0 350M Terminal-Bench Hard Overall 0% Unknown Primary source IBM-GRANITE40350M
BR-017GRANITE40350M-007 Granite 4.0 350M CritPt Overall 0% Unknown Primary source IBM-GRANITE40350M
BR-017GRANITE40350M-008 Granite 4.0 350M AA-Omniscience Overall -72.1 Unknown Primary source IBM-GRANITE40350M
BR-017GRANITE40350M-009 Granite 4.0 350M AA-Omniscience Accuracy 3.2% Unknown Primary source IBM-GRANITE40350M
BR-017GRANITE40350M-010 Granite 4.0 350M IFBench Overall 15.9% Unknown Primary source IBM-GRANITE40350M
BR-017GRANITE40350M-011 Granite 4.0 350M AA-LCR Overall 0% Unknown Primary source IBM-GRANITE40350M
BR-017GRANITE40H1B-001 Granite 4.0 H 1B Artificial Analysis Intelligence Index Overall 2.7 Unknown Primary source IBM-GRANITE40H1B
BR-017GRANITE40H1B-002 Granite 4.0 H 1B GPQA Diamond Accuracy 26.3% Unknown Primary source IBM-GRANITE40H1B
BR-017GRANITE40H1B-003 Granite 4.0 H 1B Humanity's Last Exam No tools Overall 5% Unknown Primary source IBM-GRANITE40H1B
BR-017GRANITE40H1B-004 Granite 4.0 H 1B SciCode Overall 8.2% Unknown Primary source IBM-GRANITE40H1B
BR-017GRANITE40H1B-005 Granite 4.0 H 1B tau2-bench Overall 19.6% Unknown Primary source IBM-GRANITE40H1B
BR-017GRANITE40H1B-006 Granite 4.0 H 1B Terminal-Bench Hard Overall 0% Unknown Primary source IBM-GRANITE40H1B
BR-017GRANITE40H1B-007 Granite 4.0 H 1B CritPt Overall 0% Unknown Primary source IBM-GRANITE40H1B
BR-017GRANITE40H1B-008 Granite 4.0 H 1B AA-Omniscience Overall -73.6 Unknown Primary source IBM-GRANITE40H1B
BR-017GRANITE40H1B-009 Granite 4.0 H 1B AA-Omniscience Accuracy 5.3% Unknown Primary source IBM-GRANITE40H1B
BR-017GRANITE40H1B-010 Granite 4.0 H 1B IFBench Overall 26.2% Unknown Primary source IBM-GRANITE40H1B
BR-017GRANITE40H1B-011 Granite 4.0 H 1B AA-LCR Overall 6.3% Unknown Primary source IBM-GRANITE40H1B
BR-017GRANITE40H350M-001 Granite 4.0 H 350M Artificial Analysis Intelligence Index Overall 1 Unknown Primary source IBM-GRANITE40H350M
BR-017GRANITE40H350M-002 Granite 4.0 H 350M GPQA Diamond Accuracy 25.7% Unknown Primary source IBM-GRANITE40H350M
BR-017GRANITE40H350M-003 Granite 4.0 H 350M Humanity's Last Exam No tools Overall 6.4% Unknown Primary source IBM-GRANITE40H350M
BR-017GRANITE40H350M-004 Granite 4.0 H 350M SciCode Overall 1.7% Unknown Primary source IBM-GRANITE40H350M
BR-017GRANITE40H350M-005 Granite 4.0 H 350M tau2-bench Overall 14.6% Unknown Primary source IBM-GRANITE40H350M
BR-017GRANITE40H350M-006 Granite 4.0 H 350M Terminal-Bench Hard Overall 0% Unknown Primary source IBM-GRANITE40H350M
BR-017GRANITE40H350M-007 Granite 4.0 H 350M CritPt Overall 0% Unknown Primary source IBM-GRANITE40H350M
BR-017GRANITE40H350M-008 Granite 4.0 H 350M AA-Omniscience Overall -87.2 Unknown Primary source IBM-GRANITE40H350M
BR-017GRANITE40H350M-009 Granite 4.0 H 350M AA-Omniscience Accuracy 3.7% Unknown Primary source IBM-GRANITE40H350M
BR-017GRANITE40H350M-010 Granite 4.0 H 350M IFBench Overall 17.6% Unknown Primary source IBM-GRANITE40H350M
BR-017GRANITE40H350M-011 Granite 4.0 H 350M AA-LCR Overall 0% Unknown Primary source IBM-GRANITE40H350M
BR-017GRANITE40HSMALL-001 Granite 4.0 H Small Artificial Analysis Intelligence Index Overall 5.2 Unknown Primary source IBM-GRANITE40HSMALL
BR-017GRANITE40HSMALL-002 Granite 4.0 H Small GPQA Diamond Accuracy 41.6% Unknown Primary source IBM-GRANITE40HSMALL
BR-017GRANITE40HSMALL-003 Granite 4.0 H Small Humanity's Last Exam No tools Overall 3.7% Unknown Primary source IBM-GRANITE40HSMALL
BR-017GRANITE40HSMALL-004 Granite 4.0 H Small SciCode Overall 20.9% Unknown Primary source IBM-GRANITE40HSMALL
BR-017GRANITE40HSMALL-005 Granite 4.0 H Small tau2-bench Overall 17.3% Unknown Primary source IBM-GRANITE40HSMALL
BR-017GRANITE40HSMALL-006 Granite 4.0 H Small Terminal-Bench Hard Overall 2.3% Unknown Primary source IBM-GRANITE40HSMALL
BR-017GRANITE40HSMALL-007 Granite 4.0 H Small CritPt Overall 0% Unknown Primary source IBM-GRANITE40HSMALL
BR-017GRANITE40HSMALL-008 Granite 4.0 H Small AA-Omniscience Overall -60.9 Unknown Primary source IBM-GRANITE40HSMALL
BR-017GRANITE40HSMALL-009 Granite 4.0 H Small AA-Omniscience Accuracy 14.4% Unknown Primary source IBM-GRANITE40HSMALL
BR-017GRANITE40HSMALL-010 Granite 4.0 H Small IFBench Overall 31.5% Unknown Primary source IBM-GRANITE40HSMALL
BR-017GRANITE40HSMALL-011 Granite 4.0 H Small AA-LCR Overall 9% Unknown Primary source IBM-GRANITE40HSMALL
BR-017GRANITE40MICRO-001 Granite 4.0 Micro Artificial Analysis Intelligence Index Overall 2.4 Unknown Primary source IBM-GRANITE40MICRO
BR-017GRANITE40MICRO-002 Granite 4.0 Micro GPQA Diamond Accuracy 33.6% Unknown Primary source IBM-GRANITE40MICRO
BR-017GRANITE40MICRO-003 Granite 4.0 Micro Humanity's Last Exam No tools Overall 5.1% Unknown Primary source IBM-GRANITE40MICRO
BR-017GRANITE40MICRO-004 Granite 4.0 Micro SciCode Overall 11.9% Unknown Primary source IBM-GRANITE40MICRO
BR-017GRANITE40MICRO-005 Granite 4.0 Micro tau2-bench Overall 12.6% Unknown Primary source IBM-GRANITE40MICRO
BR-017GRANITE40MICRO-006 Granite 4.0 Micro Terminal-Bench Hard Overall 1.5% Unknown Primary source IBM-GRANITE40MICRO
BR-017GRANITE40MICRO-007 Granite 4.0 Micro CritPt Overall 0% Unknown Primary source IBM-GRANITE40MICRO
BR-017GRANITE40MICRO-008 Granite 4.0 Micro AA-Omniscience Overall -77.9 Unknown Primary source IBM-GRANITE40MICRO
BR-017GRANITE40MICRO-009 Granite 4.0 Micro AA-Omniscience Accuracy 9% Unknown Primary source IBM-GRANITE40MICRO
BR-017GRANITE40MICRO-010 Granite 4.0 Micro IFBench Overall 24.8% Unknown Primary source IBM-GRANITE40MICRO
BR-017GRANITE40MICRO-011 Granite 4.0 Micro AA-LCR Overall 4% Unknown Primary source IBM-GRANITE40MICRO
BR-017GRANITE4130B-001 Granite 4.1 30B Artificial Analysis Intelligence Index Overall 8.9 Unknown Primary source IBM-GRANITE4130B
BR-017GRANITE4130B-002 Granite 4.1 30B GPQA Diamond Accuracy 48.1% Unknown Primary source IBM-GRANITE4130B
BR-017GRANITE4130B-003 Granite 4.1 30B Humanity's Last Exam No tools Overall 4.2% Unknown Primary source IBM-GRANITE4130B
BR-017GRANITE4130B-004 Granite 4.1 30B SciCode Overall 25.8% Unknown Primary source IBM-GRANITE4130B
BR-017GRANITE4130B-005 Granite 4.1 30B tau2-bench Overall 42.1% Unknown Primary source IBM-GRANITE4130B
BR-017GRANITE4130B-006 Granite 4.1 30B tau3-Banking Overall 3.9% Unknown Primary source IBM-GRANITE4130B
BR-017GRANITE4130B-007 Granite 4.1 30B Terminal-Bench Hard Overall 2.3% Unknown Primary source IBM-GRANITE4130B
BR-017GRANITE4130B-008 Granite 4.1 30B Terminal-Bench 2.1 Overall 2.6% Unknown Primary source IBM-GRANITE4130B
BR-017GRANITE4130B-009 Granite 4.1 30B CritPt Overall 0% Unknown Primary source IBM-GRANITE4130B
BR-017GRANITE4130B-010 Granite 4.1 30B AA-Omniscience Overall -67.8 Unknown Primary source IBM-GRANITE4130B
BR-017GRANITE4130B-011 Granite 4.1 30B AA-Omniscience Accuracy 14% Unknown Primary source IBM-GRANITE4130B
BR-017GRANITE4130B-012 Granite 4.1 30B IFBench Overall 44.4% Unknown Primary source IBM-GRANITE4130B
BR-017GRANITE4130B-013 Granite 4.1 30B GDPval-AA Average Normalized Score 0% Unknown Primary source IBM-GRANITE4130B
BR-017GRANITE4130B-014 Granite 4.1 30B AA-LCR Overall 18.7% Unknown Primary source IBM-GRANITE4130B
BR-017GRANITE413B-001 Granite 4.1 3B Artificial Analysis Intelligence Index Overall 4.7 Unknown Primary source IBM-GRANITE413B
BR-017GRANITE413B-002 Granite 4.1 3B GPQA Diamond Accuracy 31.4% Unknown Primary source IBM-GRANITE413B
BR-017GRANITE413B-003 Granite 4.1 3B Humanity's Last Exam No tools Overall 3.4% Unknown Primary source IBM-GRANITE413B
BR-017GRANITE413B-004 Granite 4.1 3B SciCode Overall 11.9% Unknown Primary source IBM-GRANITE413B
BR-017GRANITE413B-005 Granite 4.1 3B tau2-bench Overall 19.6% Unknown Primary source IBM-GRANITE413B
BR-017GRANITE413B-006 Granite 4.1 3B tau3-Banking Overall 1.2% Unknown Primary source IBM-GRANITE413B
BR-017GRANITE413B-007 Granite 4.1 3B Terminal-Bench Hard Overall 2.3% Unknown Primary source IBM-GRANITE413B
BR-017GRANITE413B-008 Granite 4.1 3B Terminal-Bench 2.1 Overall 1.1% Unknown Primary source IBM-GRANITE413B
BR-017GRANITE413B-009 Granite 4.1 3B CritPt Overall 0% Unknown Primary source IBM-GRANITE413B