List your company

Reasoning on HMMT25

82.8Avg@32EqLen-GRPO
9.043228.191647.3466.4884Jan 30, 2026Feb 12, 2026Feb 25, 2026Mar 10, 2026Mar 23, 2026Apr 5, 2026Apr 19, 2026

Evaluation results

MethodLinks
EqLen-GRPOBackbone=Qwen3-Next2026.0482.8————————
LUSPOBackbone=Qwen3-Next2026.0477.1————————
DAPOBackbone=Qwen3-Next2026.0476.8————————
Dr. GRPOBackbone=Qwen3-Next2026.0476.2————————
GSPOBackbone=Qwen3-Next2026.0475.4————————
GRPOBackbone=Qwen3-Next2026.0474.8————————
BaseBackbone=Qwen3-Next2026.0473.9————————
EqLen-GRPOBackbone=Qwen3-32B2026.0464————————
LUSPOBackbone=Qwen3-32B2026.0458.2————————
DAPOBackbone=Qwen3-32B2026.0457.8————————
Dr. GRPOBackbone=Qwen3-32B2026.0456.1————————
GSPOBackbone=Qwen3-32B2026.0455.4————————
GRPOBackbone=Qwen3-32B2026.0454.6————————
Type IV (STOP)Model=DS-Qwen-3-8B2026.0454.58—————311.7-80.53—
Type IV (STOP)Model=GPT-OSS-20B2026.0452.92—————216.1-76.27—
BaseBackbone=Qwen3-32B2026.0451.5————————
Type IIIModel=DS-Qwen-3-8B2026.0451.25—————314-80.38—
No pruning (Baseline)Model=DS-Qwen-3-8B2026.0451.04—————1,601——
Type IIModel=DS-Qwen-3-8B2026.0450.83—————427.8-73.28—
Type IModel=DS-Qwen-3-8B2026.0450—————322.1-79.88—
No pruning (Baseline)Model=GPT-OSS-20B2026.0448.13—————910.8——
Type IIIModel=GPT-OSS-20B2026.0446.25—————228-74.97—
Type IModel=GPT-OSS-20B2026.0445.83—————236.3-74.06—
Type IIModel=GPT-OSS-20B2026.0445.42—————336.9-63.01—
Type IV (STOP)Model=DS-Qwen-2.5-7B2026.0427.08—————211.6-73.84—
Type IModel=DS-Qwen-2.5-7B2026.0425—————219.5-72.87—
Type IIIModel=DS-Qwen-2.5-7B2026.0424.58—————216.1-73.28—
No pruning (Baseline)Model=DS-Qwen-2.5-7B2026.0423.91—————808.9——
Type IIModel=DS-Qwen-2.5-7B2026.0423.33—————330.8-59.11—
Type IV (STOP)Model=DS-Qwen-2.5-1.5B2026.0417.92—————215.5-74.84—
Type IIIModel=DS-Qwen-2.5-1.5B2026.0417.08—————220.9-74.21—
Type IModel=DS-Qwen-2.5-1.5B2026.0415.83—————224.2-73.82—
No pruning (Baseline)Model=DS-Qwen-2.5-1.5B2026.0415.05—————856.4——
Type IIModel=DS-Qwen-2.5-1.5B2026.0415—————337.2-60.63—
CraEGTemperature=1, Top-p=1, Backbone=Qwen3-1.7B2026.0114.5830.5851.9315.46—————
Standard SamplingTemperature=1, Top-p=1, Backbone=Qwen3-1.7B2026.0113.8527.7451.0114.78—————
CraEGTemperature=0.7, Top-p=0.95, Backbone=Qwen3-1.7B2026.0112.624.4342.2812.1—————
Standard SamplingTemperature=0.7, Top-p=0.95, Backbone=Qwen3-1.7B2026.0111.8821.4441.5312.02—————
ASCType=Handcrafted, Base Model=DeepSeek-R1-Distill-Llama-8B2026.05——————582,700—26.5
AutoTTSType=Discovered, Base Model=DeepSeek-R1-Distill-Llama-8B, β=12026.05——————533,900—27.2
AutoTTSType=Discovered, Base Model=DeepSeek-R1-Distill-Llama-8B, β=0.52026.05——————279,000—26.3
ESCType=Handcrafted, Base Model=DeepSeek-R1-Distill-Llama-8B2026.05——————952,100—26.7
MULTIVERSEReasoning Type=Parallel2025.12————1,465.12.1———
NPR-Inst.Reasoning Type=Parallel2025.12————2,784.14.1———
SC@64Type=Handcrafted, Base Model=DeepSeek-R1-Distill-Llama-8B2026.05——————985,700—26.7
SRReasoning Type=Sequential baseline2025.12————683.81———