List your company

Macro-average Exact Match on ShellOps-Pro

53.3Macro-average Exact Match AccuracyKimi-K2.6
16.58826.11935.6545.181May 8, 2026

Evaluation results

MethodLinks
Kimi-K2.6Hmax=10, Paradigm=Frontier Agentic Inference2026.0553.3
Kimi-K2.6Hmax=8, Paradigm=Frontier Agentic Inference2026.0547.9
Kimi-K2.6Hmax=6, Paradigm=Frontier Agentic Inference2026.0545.9
GLM-5.1Hmax=10, Paradigm=Frontier Agentic Inference2026.0540.7
GLM-5.1Hmax=8, Paradigm=Frontier Agentic Inference2026.0539.1
GLM-5.1Hmax=6, Paradigm=Frontier Agentic Inference2026.0534.7
A3 (σ-Reveal)Hmax=10, Paradigm=Agentic RL, Backbone=Qwen3-14B2026.0531.1
A3 (σ-Reveal)Hmax=8, Paradigm=Agentic RL, Backbone=Qwen3-14B2026.0530.5
A3 (σ-Reveal)Hmax=6, Paradigm=Agentic RL, Backbone=Qwen3-14B2026.0529.9
Qwen3-235B-A22BHmax=8, Paradigm=Frontier Agentic Inference2026.0529.3
Qwen3-235B-A22BHmax=10, Paradigm=Frontier Agentic Inference2026.0528.3
GiGPOHmax=6, Paradigm=Agentic RL, Backbone=Qwen3-14B2026.0527.1
Qwen3-235B-A22BHmax=6, Paradigm=Frontier Agentic Inference2026.0526.7
GiGPOHmax=8, Paradigm=Agentic RL, Backbone=Qwen3-14B2026.0526.3
A3 (Vanilla)Hmax=8, Paradigm=Agentic RL, Backbone=Qwen3-14B2026.0525.9
GiGPOHmax=10, Paradigm=Agentic RL, Backbone=Qwen3-14B2026.0525.7
GSPOHmax=10, Paradigm=Agentic RL, Backbone=Qwen3-14B2026.0525.5
A3 (Vanilla)Hmax=10, Paradigm=Agentic RL, Backbone=Qwen3-14B2026.0525.3
GSPOHmax=8, Paradigm=Agentic RL, Backbone=Qwen3-14B2026.0524.9
GSPOHmax=6, Paradigm=Agentic RL, Backbone=Qwen3-14B2026.0524.4
A3 (Vanilla)Hmax=6, Paradigm=Agentic RL, Backbone=Qwen3-14B2026.0522.9
HGPOHmax=10, Paradigm=Agentic RL, Backbone=Qwen3-14B2026.0522.8
ReACTHmax=8, Paradigm=Agentic Inference, Backbone=Qwen3-14B2026.0522.3
ReACTHmax=10, Paradigm=Agentic Inference, Backbone=Qwen3-14B2026.0522
HGPOHmax=8, Paradigm=Agentic RL, Backbone=Qwen3-14B2026.0521.9
LATSHmax=8, Paradigm=Agentic Inference, Backbone=Qwen3-14B2026.0521.7
LATSHmax=6, Paradigm=Agentic Inference, Backbone=Qwen3-14B2026.0521.1
rStarHmax=8, Paradigm=Agentic Inference, Backbone=Qwen3-14B2026.0521.1
rStarHmax=10, Paradigm=Agentic Inference, Backbone=Qwen3-14B2026.0520.4
RetroAgentHmax=10, Paradigm=Agentic RL, Backbone=Qwen3-14B2026.0520
LATSHmax=10, Paradigm=Agentic Inference, Backbone=Qwen3-14B2026.0519.7
HGPOHmax=6, Paradigm=Agentic RL, Backbone=Qwen3-14B2026.0519.5
ReACTHmax=6, Paradigm=Agentic Inference, Backbone=Qwen3-14B2026.0519.3
rStarHmax=6, Paradigm=Agentic Inference, Backbone=Qwen3-14B2026.0519.3
RetroAgentHmax=8, Paradigm=Agentic RL, Backbone=Qwen3-14B2026.0519.2
RetroAgentHmax=6, Paradigm=Agentic RL, Backbone=Qwen3-14B2026.0518