List your company

Mathematical Reasoning on HLE Maths (Acc, Cost)

38.2AccuracyMAS-Zero
1.352810.918920.48530.0511Jun 11, 2026

Evaluation results

MethodLinks
MAS-ZeroLLM Backbone=GPT-52026.0638.21,288.3
MAS-OrchestraLLM Backbone=GPT-52026.0637.64147.49
DyLANLLM Backbone=GPT-52026.0635.51115.1
MaASLLM Backbone=GPT-52026.0635.32221.2
ADASLLM Backbone=GPT-52026.0634.6846.9
MaASLLM Backbone=Gemini-2.5-Pro2026.0634.52248.78
CoT-SCLLM Backbone=GPT-52026.0633.92116.2
AFlowLLM Backbone=GPT-52026.0632.73784.6
DyLANLLM Backbone=Gemini-2.5-Pro2026.0632.14396.98
CoTLLM Backbone=GPT-52026.0629.8733.5
MAS-ZeroLLM Backbone=Gemini-2.5-Pro2026.0629.5—
ADASLLM Backbone=Gemini-2.5-Pro2026.0627.981,896
CoT-SCLLM Backbone=Gemini-2.5-Pro2026.0626.19243.81
CoTLLM Backbone=Gemini-2.5-Pro2026.0625.647.71
AFlowLLM Backbone=Gemini-2.5-Pro2026.0619.05302.59
MAS-ZeroLLM Backbone=GPT-OSS-120B2026.0615.7515.62
MaASLLM Backbone=GPT-OSS-120B2026.0615.482.6
CoT-SCLLM Backbone=GPT-OSS-120B2026.0613.893.9
AFlowLLM Backbone=GPT-OSS-120B2026.069.5123
DyLANLLM Backbone=GPT-OSS-120B2026.069.321.6
MAS-OrchestraLLM Backbone=GPT-OSS-120B2026.069.322
CoTLLM Backbone=GPT-OSS-120B2026.068.730.3
ADASLLM Backbone=GPT-OSS-120B2026.067.931.9
CoT-SCLLM Backbone=GPT-4o2026.064.768.7
CoTLLM Backbone=GPT-4o2026.064.61.3
MaASLLM Backbone=GPT-4o2026.064.375.99
ADASLLM Backbone=GPT-4o2026.063.850.6
DyLANLLM Backbone=GPT-4o2026.063.5712.9
MAS-OrchestraLLM Backbone=GPT-4o2026.063.379.3
MAS-ZeroLLM Backbone=GPT-4o2026.063.17249.8
AFlowLLM Backbone=GPT-4o2026.062.77292.6