List your company

Reasoning on AALCR

48.75Accuracygpt-oss-120B
23.84230.308536.77543.2415Jan 27, 2026Jan 29, 2026Feb 1, 2026Feb 4, 2026Feb 6, 2026Feb 9, 2026Feb 12, 2026

Evaluation results

MethodLinks
gpt-oss-120BReasoning effort=High, KV cache precision=BF162026.0248.75
gpt-oss-120BReasoning effort=High, KV cache precision=FP82026.0246.75
gpt-oss-puzzle-88BReasoning effort=High, KV cache precision=BF162026.0242.25
gpt-oss-120BReasoning effort=Medium, KV cache precision=FP82026.0241.5
gpt-oss-puzzle-88BReasoning effort=High, KV cache precision=FP82026.0240.75
gpt-oss-120BReasoning effort=Medium, KV cache precision=BF162026.0239.25
gpt-oss-puzzle-88BReasoning effort=Medium, KV cache precision=BF162026.0236
BF16Precision=BF16, Backbone=Nemotron 3 Nano2026.0135.9
gpt-oss-puzzle-88BReasoning effort=Medium, KV cache precision=FP82026.0235.75
gpt-oss-120BReasoning effort=Low, KV cache precision=BF162026.0235.25
gpt-oss-120BReasoning effort=Low, KV cache precision=FP82026.0234.75
NVFP4 QADPrecision=NVFP4, Type=QAD, Backbone=Nemotron 3 Nano2026.0134.3
gpt-oss-puzzle-88BReasoning effort=Low, KV cache precision=BF162026.0231.75
NVFP4 PTQPrecision=NVFP4, Type=PTQ, Backbone=Nemotron 3 Nano2026.0131.3
gpt-oss-puzzle-88BReasoning effort=Low, KV cache precision=FP82026.0228.75
NVFP4 QATPrecision=NVFP4, Type=QAT, Backbone=Nemotron 3 Nano2026.0124.8