Inference Chip Index

← All slices

gpt-oss-120b · Interactive

gpt-oss-120b / Interactive / Tokens/s

v6.0|closed|gpt-oss-120b|Interactive|Tokens/s|official-system

Metric: Performance_Result (Tokens/s) · winning: higher · 4 ranking-eligible rows · vendors 1 · families 2 · never mixed with other slices

All systems (official)
RankPerformanceUnitSystemSubmitterAcceleratorSource
1677,199.0000Tokens/sNVIDIA GB300 NVL72 (72x GB300-288GB_aarch64, TensorRT)NVIDIANVIDIA GB300source
2624,929.0000Tokens/sNVIDIA GB200 NVL72 (72x GB200-186GB_aarch64, TensorRT)NVIDIANVIDIA GB200source
326,005.8000Tokens/sXA NB3I-E12ASUSTeKNVIDIA B300-SXM-270GBsource
413,155.3000Tokens/sNebius B200 n1 (8x B200-SXM-180GB, TensorRT)NebiusNVIDIA B200-SXM-180GBsource