Reasoning on AALCR
48.75Accuracygpt-oss-120B
Evaluation Results
| Method | Links | |
|---|---|---|
| gpt-oss-120BReasoning effort=High, KV cache precision=BF162026.02 | 48.75 | |
| gpt-oss-120BReasoning effort=High, KV cache precision=FP82026.02 | 46.75 | |
| gpt-oss-puzzle-88BReasoning effort=High, KV cache precision=BF162026.02 | 42.25 | |
| gpt-oss-120BReasoning effort=Medium, KV cache precision=FP82026.02 | 41.5 | |
| gpt-oss-puzzle-88BReasoning effort=High, KV cache precision=FP82026.02 | 40.75 | |
| gpt-oss-120BReasoning effort=Medium, KV cache precision=BF162026.02 | 39.25 | |
| gpt-oss-puzzle-88BReasoning effort=Medium, KV cache precision=BF162026.02 | 36 | |
| BF16Precision=BF16, Backbone=Nemotron 3 Nano2026.01 | 35.9 | |
| gpt-oss-puzzle-88BReasoning effort=Medium, KV cache precision=FP82026.02 | 35.75 | |
| gpt-oss-120BReasoning effort=Low, KV cache precision=BF162026.02 | 35.25 | |
| gpt-oss-120BReasoning effort=Low, KV cache precision=FP82026.02 | 34.75 | |
| NVFP4 QADPrecision=NVFP4, Type=QAD, Backbone=Nemotron 3 Nano2026.01 | 34.3 | |
| gpt-oss-puzzle-88BReasoning effort=Low, KV cache precision=BF162026.02 | 31.75 | |
| NVFP4 PTQPrecision=NVFP4, Type=PTQ, Backbone=Nemotron 3 Nano2026.01 | 31.3 | |
| gpt-oss-puzzle-88BReasoning effort=Low, KV cache precision=FP82026.02 | 28.75 | |
| NVFP4 QATPrecision=NVFP4, Type=QAT, Backbone=Nemotron 3 Nano2026.01 | 24.8 |