StepFun

Provider prefix
STPFN
Benchmark Record namespace
026

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-026STEP35FLASH-001 Step 3.5 Flash Artificial Analysis Intelligence Index Overall 25.5 Unknown Primary source STPFN-STEP35FLASH
BR-026STEP35FLASH-002 Step 3.5 Flash GPQA Diamond Accuracy 83.1% Unknown Primary source STPFN-STEP35FLASH
BR-026STEP35FLASH-003 Step 3.5 Flash Humanity's Last Exam No tools Overall 19.1% Unknown Primary source STPFN-STEP35FLASH
BR-026STEP35FLASH-004 Step 3.5 Flash SciCode Overall 40.4% Unknown Primary source STPFN-STEP35FLASH
BR-026STEP35FLASH-005 Step 3.5 Flash tau2-bench Overall 94.4% Unknown Primary source STPFN-STEP35FLASH
BR-026STEP35FLASH-006 Step 3.5 Flash Terminal-Bench Hard Overall 27.3% Unknown Primary source STPFN-STEP35FLASH
BR-026STEP35FLASH-007 Step 3.5 Flash CritPt Overall 2.5% Unknown Primary source STPFN-STEP35FLASH
BR-026STEP35FLASH-008 Step 3.5 Flash AA-Omniscience Overall -40.9 Unknown Primary source STPFN-STEP35FLASH
BR-026STEP35FLASH-009 Step 3.5 Flash AA-Omniscience Accuracy 23.9% Unknown Primary source STPFN-STEP35FLASH
BR-026STEP35FLASH-010 Step 3.5 Flash IFBench Overall 64.6% Unknown Primary source STPFN-STEP35FLASH
BR-026STEP35FLASH-011 Step 3.5 Flash AA-LCR Overall 43% Unknown Primary source STPFN-STEP35FLASH
BR-026STEP35FLASH2603-001 Step 3.5 Flash 2603 Artificial Analysis Intelligence Index Overall 26 Unknown Primary source STPFN-STEP35FLASH2603
BR-026STEP35FLASH2603-002 Step 3.5 Flash 2603 GPQA Diamond Accuracy 82.6% Unknown Primary source STPFN-STEP35FLASH2603
BR-026STEP35FLASH2603-003 Step 3.5 Flash 2603 Humanity's Last Exam No tools Overall 22.6% Unknown Primary source STPFN-STEP35FLASH2603
BR-026STEP35FLASH2603-004 Step 3.5 Flash 2603 SciCode Overall 38.5% Unknown Primary source STPFN-STEP35FLASH2603
BR-026STEP35FLASH2603-005 Step 3.5 Flash 2603 tau2-bench Overall 87.4% Unknown Primary source STPFN-STEP35FLASH2603
BR-026STEP35FLASH2603-006 Step 3.5 Flash 2603 Terminal-Bench Hard Overall 32.6% Unknown Primary source STPFN-STEP35FLASH2603
BR-026STEP35FLASH2603-007 Step 3.5 Flash 2603 CritPt Overall 2.3% Unknown Primary source STPFN-STEP35FLASH2603
BR-026STEP35FLASH2603-008 Step 3.5 Flash 2603 AA-Omniscience Overall -43.7 Unknown Primary source STPFN-STEP35FLASH2603
BR-026STEP35FLASH2603-009 Step 3.5 Flash 2603 AA-Omniscience Accuracy 25% Unknown Primary source STPFN-STEP35FLASH2603
BR-026STEP35FLASH2603-010 Step 3.5 Flash 2603 IFBench Overall 66.5% Unknown Primary source STPFN-STEP35FLASH2603
BR-026STEP35FLASH2603-011 Step 3.5 Flash 2603 AA-LCR Overall 54.3% Unknown Primary source STPFN-STEP35FLASH2603
BR-026STEP37FLASH-001 Step 3.7 Flash Artificial Analysis Intelligence Index Overall 30.3 Unknown Primary source STPFN-STEP37FLASH
BR-026STEP37FLASH-002 Step 3.7 Flash GPQA Diamond Accuracy 80.9% Unknown Primary source STPFN-STEP37FLASH
BR-026STEP37FLASH-003 Step 3.7 Flash Humanity's Last Exam No tools Overall 19.9% Unknown Primary source STPFN-STEP37FLASH
BR-026STEP37FLASH-004 Step 3.7 Flash SciCode Overall 40% Unknown Primary source STPFN-STEP37FLASH
BR-026STEP37FLASH-005 Step 3.7 Flash tau2-bench Overall 98.5% Unknown Primary source STPFN-STEP37FLASH
BR-026STEP37FLASH-006 Step 3.7 Flash tau3-Banking Overall 11.3% Unknown Primary source STPFN-STEP37FLASH
BR-026STEP37FLASH-007 Step 3.7 Flash Terminal-Bench Hard Overall 35.6% Unknown Primary source STPFN-STEP37FLASH
BR-026STEP37FLASH-008 Step 3.7 Flash Terminal-Bench 2.1 Overall 39.3% Unknown Primary source STPFN-STEP37FLASH
BR-026STEP37FLASH-009 Step 3.7 Flash CritPt Overall 2.3% Unknown Primary source STPFN-STEP37FLASH
BR-026STEP37FLASH-010 Step 3.7 Flash AA-Omniscience Overall -37.5 Unknown Primary source STPFN-STEP37FLASH
BR-026STEP37FLASH-011 Step 3.7 Flash AA-Omniscience Accuracy 25.4% Unknown Primary source STPFN-STEP37FLASH
BR-026STEP37FLASH-012 Step 3.7 Flash IFBench Overall 67.3% Unknown Primary source STPFN-STEP37FLASH
BR-026STEP37FLASH-013 Step 3.7 Flash APEX-Agents Overall 14.8% Unknown Primary source STPFN-STEP37FLASH
BR-026STEP37FLASH-014 Step 3.7 Flash ITBench SRE Overall 30.3% Unknown Primary source STPFN-STEP37FLASH
BR-026STEP37FLASH-015 Step 3.7 Flash GDPval-AA Average Normalized Score 25.9% Unknown Primary source STPFN-STEP37FLASH
BR-026STEP37FLASH-016 Step 3.7 Flash MMMU-Pro Overall 75.3% Unknown Primary source STPFN-STEP37FLASH
BR-026STEP37FLASH-017 Step 3.7 Flash AA-LCR Overall 63.7% Unknown Primary source STPFN-STEP37FLASH
BR-026STEP3VL10B-001 Step3 VL 10B Artificial Analysis Intelligence Index Overall 9.5 Unknown Primary source STPFN-STEP3VL10B
BR-026STEP3VL10B-002 Step3 VL 10B GPQA Diamond Accuracy 69% Unknown Primary source STPFN-STEP3VL10B
BR-026STEP3VL10B-003 Step3 VL 10B Humanity's Last Exam No tools Overall 10.2% Unknown Primary source STPFN-STEP3VL10B
BR-026STEP3VL10B-004 Step3 VL 10B SciCode Overall 31.1% Unknown Primary source STPFN-STEP3VL10B
BR-026STEP3VL10B-005 Step3 VL 10B tau2-bench Overall 16.1% Unknown Primary source STPFN-STEP3VL10B
BR-026STEP3VL10B-006 Step3 VL 10B Terminal-Bench Hard Overall 5.3% Unknown Primary source STPFN-STEP3VL10B
BR-026STEP3VL10B-007 Step3 VL 10B CritPt Overall 0% Unknown Primary source STPFN-STEP3VL10B
BR-026STEP3VL10B-008 Step3 VL 10B AA-Omniscience Overall -59 Unknown Primary source STPFN-STEP3VL10B
BR-026STEP3VL10B-009 Step3 VL 10B AA-Omniscience Accuracy 12.7% Unknown Primary source STPFN-STEP3VL10B
BR-026STEP3VL10B-010 Step3 VL 10B IFBench Overall 50.2% Unknown Primary source STPFN-STEP3VL10B
BR-026STEP3VL10B-011 Step3 VL 10B MMMU-Pro Overall 64% Unknown Primary source STPFN-STEP3VL10B
BR-026STEP3VL10B-012 Step3 VL 10B AA-LCR Overall 0% Unknown Primary source STPFN-STEP3VL10B