List your company
ResearchFormerly WizWand

Reasoning on Reasoning Benchmark Suite Aggregate

59.44Average Scoregpt-oss-puzzle-88B
41.198445.934250.6755.4058Apr 15, 2025Jun 4, 2025Jul 25, 2025Sep 13, 2025Nov 3, 2025Dec 23, 2025Feb 12, 2026
Updated 7mo ago

Evaluation results

MethodLinks
gpt-oss-puzzle-88BReasoning effort=High, KV cache precision=BF162026.0259.44
gpt-oss-120BReasoning effort=High, KV cache precision=BF162026.0259.2
gpt-oss-puzzle-88BReasoning effort=High, KV cache precision=FP82026.0258.67
gpt-oss-120BReasoning effort=High, KV cache precision=FP82026.0258.19
NEMOTRON-CROSSTHINKCategory=Data Source, Blend=Bgpr↑2025.0458.12
NEMOTRON-CROSSTHINKCategory=Single Source, Blend=Bonly_mr2025.0457.82
NEMOTRON-CROSSTHINKCategory=Data Source, Blend=Bmr↑2025.0457.72
NEMOTRON-CROSSTHINKCategory=Question Types, Blend=Bopen↑2025.0457.49
NEMOTRON-CROSSTHINKCategory=Data Usefulness, Blend=Bscore2025.0456.95
NEMOTRON-CROSSTHINKCategory=Question Types, Blend=Bmcq↑2025.0456.89
R-Few (5%)Backbone=Qwen3-8B-Base, Methodology=R-Few, Supervision Ratio=5%2025.1256.7
gpt-oss-puzzle-88BReasoning effort=Medium, KV cache precision=BF162026.0256.64
General-ReasonerBackbone=Qwen3-8B-Base, Methodology=General-Reasoner, Supervision Ratio=232k WebInstruct2025.1256
NEMOTRON-CROSSTHINKBlend=Bnd2025.0455.66
SPICEBackbone=Qwen3-8B-Base, Methodology=SPICE, Supervision Ratio=None2025.1255.4
ORZModel=ORZ2025.0455.2
R-Few (1%)Backbone=Qwen3-8B-Base, Methodology=R-Few, Supervision Ratio=1%2025.1255.1
gpt-oss-puzzle-88BReasoning effort=Medium, KV cache precision=FP82026.0254.93
General-ReasonerBackbone=Qwen3-4B-Base, Methodology=General-Reasoner, Supervision Ratio=232k WebInstruct2025.1254.3
R-ZeroBackbone=Qwen3-8B-Base, Methodology=R-Zero, Supervision Ratio=None2025.1253.7
gpt-oss-120BReasoning effort=Medium, KV cache precision=BF162026.0253.66
NEMOTRON-CROSSTHINKCategory=Single Source, Blend=Bonly_gpr2025.0453.3
gpt-oss-120BReasoning effort=Medium, KV cache precision=FP82026.0252.89
Absolute ZeroBackbone=Qwen3-8B-Base, Methodology=Absolute Zero, Supervision Ratio=None2025.1252.8
SPICEBackbone=Qwen3-4B-Base, Methodology=SPICE, Supervision Ratio=None2025.1251.4
R-Few (5%)Backbone=Qwen3-4B-Base, Methodology=R-Few, Supervision Ratio=5%2025.1250.7
gpt-oss-puzzle-88BReasoning effort=Low, KV cache precision=BF162026.0250.61
R-Few (1%)Backbone=Qwen3-4B-Base, Methodology=R-Few, Supervision Ratio=1%2025.1249.9
Base ModelBackbone=Qwen3-8B-Base, Methodology=Base, Supervision Ratio=None2025.1249.9
gpt-oss-puzzle-88BReasoning effort=Low, KV cache precision=FP82026.0248.38
R-ZeroBackbone=Qwen3-4B-Base, Methodology=R-Zero, Supervision Ratio=None2025.1248.2
Absolute ZeroBackbone=Qwen3-4B-Base, Methodology=Absolute Zero, Supervision Ratio=None2025.1246.9
gpt-oss-120BReasoning effort=Low, KV cache precision=BF162026.0245.41
MModel=M2025.0444.75
gpt-oss-120BReasoning effort=Low, KV cache precision=FP82026.0244.71
Base ModelBackbone=Qwen3-4B-Base, Methodology=Base, Supervision Ratio=None2025.1241.9