BENCHMARK REGISTRY
Public Artificial Intelligence Benchmark Records Database

Upstage

Provider prefix
UPSTG
Benchmark Record namespace
024

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-024SOLARMINI-001 Solar Mini Artificial Analysis Intelligence Index Overall 6.2 Unknown Primary source UPSTG-SOLARMINI
BR-024SOLARMINI-002 Solar Mini tau2-bench Overall 20.2% Unknown Primary source UPSTG-SOLARMINI
BR-024SOLAROPEN100B-001 Solar Open 100B Artificial Analysis Intelligence Index Overall 15.1 Unknown Primary source UPSTG-SOLAROPEN100B
BR-024SOLAROPEN100B-002 Solar Open 100B GPQA Diamond Accuracy 65.7% Unknown Primary source UPSTG-SOLAROPEN100B
BR-024SOLAROPEN100B-003 Solar Open 100B Humanity's Last Exam No tools Overall 9.2% Unknown Primary source UPSTG-SOLAROPEN100B
BR-024SOLAROPEN100B-004 Solar Open 100B SciCode Overall 26.9% Unknown Primary source UPSTG-SOLAROPEN100B
BR-024SOLAROPEN100B-005 Solar Open 100B tau2-bench Overall 48.2% Unknown Primary source UPSTG-SOLAROPEN100B
BR-024SOLAROPEN100B-006 Solar Open 100B Terminal-Bench Hard Overall 2.3% Unknown Primary source UPSTG-SOLAROPEN100B
BR-024SOLAROPEN100B-007 Solar Open 100B CritPt Overall 0% Unknown Primary source UPSTG-SOLAROPEN100B
BR-024SOLAROPEN100B-008 Solar Open 100B AA-Omniscience Overall -54.1 Unknown Primary source UPSTG-SOLAROPEN100B
BR-024SOLAROPEN100B-009 Solar Open 100B AA-Omniscience Accuracy 18.1% Unknown Primary source UPSTG-SOLAROPEN100B
BR-024SOLAROPEN100B-010 Solar Open 100B IFBench Overall 57.7% Unknown Primary source UPSTG-SOLAROPEN100B
BR-024SOLAROPEN100B-011 Solar Open 100B AA-LCR Overall 36% Unknown Primary source UPSTG-SOLAROPEN100B
BR-024SOLARPRO2-001 Solar Pro 2 Artificial Analysis Intelligence Index Overall 7.8 Unknown Primary source UPSTG-SOLARPRO2
BR-024SOLARPRO2-002 Solar Pro 2 GPQA Diamond Accuracy 56.1% Unknown Primary source UPSTG-SOLARPRO2
BR-024SOLARPRO2-003 Solar Pro 2 Humanity's Last Exam No tools Overall 3.8% Unknown Primary source UPSTG-SOLARPRO2
BR-024SOLARPRO2-004 Solar Pro 2 SciCode Overall 24.8% Unknown Primary source UPSTG-SOLARPRO2
BR-024SOLARPRO2-005 Solar Pro 2 tau2-bench Overall 31.9% Unknown Primary source UPSTG-SOLARPRO2
BR-024SOLARPRO2-006 Solar Pro 2 Terminal-Bench Hard Overall 4.5% Unknown Primary source UPSTG-SOLARPRO2
BR-024SOLARPRO2-007 Solar Pro 2 CritPt Overall 0% Unknown Primary source UPSTG-SOLARPRO2
BR-024SOLARPRO2-008 Solar Pro 2 AA-Omniscience Overall -61.7 Unknown Primary source UPSTG-SOLARPRO2
BR-024SOLARPRO2-009 Solar Pro 2 AA-Omniscience Accuracy 15.6% Unknown Primary source UPSTG-SOLARPRO2
BR-024SOLARPRO2-010 Solar Pro 2 IFBench Overall 33.7% Unknown Primary source UPSTG-SOLARPRO2
BR-024SOLARPRO2-011 Solar Pro 2 AA-LCR Overall 0% Unknown Primary source UPSTG-SOLARPRO2
BR-024SOLARPRO2-012 Solar Pro 2 Artificial Analysis Intelligence Index Overall 9 Unknown Primary source UPSTG-SOLARPRO2
BR-024SOLARPRO2-013 Solar Pro 2 GPQA Diamond Accuracy 68.7% Unknown Primary source UPSTG-SOLARPRO2
BR-024SOLARPRO2-014 Solar Pro 2 Humanity's Last Exam No tools Overall 7% Unknown Primary source UPSTG-SOLARPRO2
BR-024SOLARPRO2-015 Solar Pro 2 SciCode Overall 30.2% Unknown Primary source UPSTG-SOLARPRO2
BR-024SOLARPRO2-016 Solar Pro 2 tau2-bench Overall 28.1% Unknown Primary source UPSTG-SOLARPRO2
BR-024SOLARPRO2-017 Solar Pro 2 Terminal-Bench Hard Overall 3% Unknown Primary source UPSTG-SOLARPRO2
BR-024SOLARPRO2-018 Solar Pro 2 CritPt Overall 0% Unknown Primary source UPSTG-SOLARPRO2
BR-024SOLARPRO2-019 Solar Pro 2 AA-Omniscience Overall -56.6 Unknown Primary source UPSTG-SOLARPRO2
BR-024SOLARPRO2-020 Solar Pro 2 AA-Omniscience Accuracy 19.5% Unknown Primary source UPSTG-SOLARPRO2
BR-024SOLARPRO2-021 Solar Pro 2 IFBench Overall 37.1% Unknown Primary source UPSTG-SOLARPRO2
BR-024SOLARPRO2-022 Solar Pro 2 AA-LCR Overall 0% Unknown Primary source UPSTG-SOLARPRO2
BR-024SOLARPRO2PREVIEW-001 Solar Pro 2 (Preview) Artificial Analysis Intelligence Index Overall 10 Unknown Primary source UPSTG-SOLARPRO2PREVIEW
BR-024SOLARPRO2PREVIEW-002 Solar Pro 2 (Preview) GPQA Diamond Accuracy 54.4% Unknown Primary source UPSTG-SOLARPRO2PREVIEW
BR-024SOLARPRO2PREVIEW-003 Solar Pro 2 (Preview) Humanity's Last Exam No tools Overall 3.8% Unknown Primary source UPSTG-SOLARPRO2PREVIEW
BR-024SOLARPRO2PREVIEW-004 Solar Pro 2 (Preview) SciCode Overall 27.2% Unknown Primary source UPSTG-SOLARPRO2PREVIEW
BR-024SOLARPRO2PREVIEW-005 Solar Pro 2 (Preview) Artificial Analysis Intelligence Index Overall 12.5 Unknown Primary source UPSTG-SOLARPRO2PREVIEW
BR-024SOLARPRO2PREVIEW-006 Solar Pro 2 (Preview) GPQA Diamond Accuracy 57.8% Unknown Primary source UPSTG-SOLARPRO2PREVIEW
BR-024SOLARPRO2PREVIEW-007 Solar Pro 2 (Preview) Humanity's Last Exam No tools Overall 5.7% Unknown Primary source UPSTG-SOLARPRO2PREVIEW
BR-024SOLARPRO2PREVIEW-008 Solar Pro 2 (Preview) SciCode Overall 16.4% Unknown Primary source UPSTG-SOLARPRO2PREVIEW
BR-024SOLARPRO3-001 Solar Pro 3 Artificial Analysis Intelligence Index Overall 14.1 Unknown Primary source UPSTG-SOLARPRO3
BR-024SOLARPRO3-002 Solar Pro 3 GPQA Diamond Accuracy 72.4% Unknown Primary source UPSTG-SOLARPRO3
BR-024SOLARPRO3-003 Solar Pro 3 Humanity's Last Exam No tools Overall 10.1% Unknown Primary source UPSTG-SOLARPRO3
BR-024SOLARPRO3-004 Solar Pro 3 SciCode Overall 24.7% Unknown Primary source UPSTG-SOLARPRO3
BR-024SOLARPRO3-005 Solar Pro 3 tau2-bench Overall 86.3% Unknown Primary source UPSTG-SOLARPRO3
BR-024SOLARPRO3-006 Solar Pro 3 tau3-Banking Overall 8% Unknown Primary source UPSTG-SOLARPRO3
BR-024SOLARPRO3-007 Solar Pro 3 Terminal-Bench Hard Overall 7.6% Unknown Primary source UPSTG-SOLARPRO3
BR-024SOLARPRO3-008 Solar Pro 3 Terminal-Bench 2.1 Overall 12% Unknown Primary source UPSTG-SOLARPRO3
BR-024SOLARPRO3-009 Solar Pro 3 CritPt Overall 0% Unknown Primary source UPSTG-SOLARPRO3
BR-024SOLARPRO3-010 Solar Pro 3 AA-Omniscience Overall -53.8 Unknown Primary source UPSTG-SOLARPRO3
BR-024SOLARPRO3-011 Solar Pro 3 AA-Omniscience Accuracy 18.1% Unknown Primary source UPSTG-SOLARPRO3
BR-024SOLARPRO3-012 Solar Pro 3 IFBench Overall 71.2% Unknown Primary source UPSTG-SOLARPRO3
BR-024SOLARPRO3-013 Solar Pro 3 GDPval-AA Average Normalized Score 0% Unknown Primary source UPSTG-SOLARPRO3
BR-024SOLARPRO3-014 Solar Pro 3 AA-LCR Overall 27% Unknown Primary source UPSTG-SOLARPRO3