List your company

General Reasoning and Coding on OOD Suite (ARC-c, GPQA, MMLU-Pro, LiveCodeBench)

96.6ARC-c (pass@1)w4a16 QaRL TBPO
8.30431.22754.1577.073Apr 9, 2026

Evaluation results

MethodLinks
w4a16 QaRL TBPOModel=Qwen3-30B-A3B-Base, Precision=w4a16, RL Algorithm=QaRL TBPO2026.0496.648.26855.467.05
BF16 GSPOModel=Qwen3-30B-A3B-Base, Precision=BF16, RL Algorithm=GSPO2026.0495.250.170.355.867.8
BF16 GRPOModel=Qwen3-8B-Base, Precision=BF16, RL Algorithm=GRPO2026.049346.365.145.762.5
w4a16 QaRL TBPOModel=Qwen3-8B-Base, Precision=w4a16, RL Algorithm=QaRL TBPO2026.0492.34563.843.461
w4a16 rollout GRPOModel=Qwen3-8B-Base, Precision=w4a16, Rollout Strategy=rollout, RL Algorithm=GRPO2026.0491.643.961.541.459.5
w4a16 rollout GSPOModel=Qwen3-30B-A3B-Base, Precision=w4a16, Rollout Strategy=rollout, RL Algorithm=GSPO2026.0489.342.465.347.961.2
w4a16 QaRL TBPOModel=Qwen2.5-7B-Math, Precision=w4a16, RL Algorithm=QaRL TBPO2026.0481.137.145.813.944.4
BF16 GRPOModel=Qwen2.5-7B-Math, Precision=BF16, RL Algorithm=GRPO2026.0480.438.246.314.644.8
w4a16 rollout GRPOModel=Qwen2.5-7B-Math, Precision=w4a16, Rollout Strategy=rollout, RL Algorithm=GRPO2026.0473.931.6408.738.5
Qwen2.5-7B-MathModel=Qwen2.5-7B-Math2026.0462.628.532.1832.8
Qwen3-30B-A3B-BaseModel=Qwen3-30B-A3B-Base2026.0461.334.852.528.544.2
BF16 GRPOModel=Qwen2.5-1.5B-Math, Precision=BF16, RL Algorithm=GRPO2026.0458.927.826.711.931.3
w4a16 QaRL TBPOModel=Qwen2.5-1.5B-Math, Precision=w4a16, RL Algorithm=QaRL TBPO2026.0457.621.125.38.128
w4a16 rollout GRPOModel=Qwen2.5-1.5B-Math, Precision=w4a16, Rollout Strategy=rollout, RL Algorithm=GRPO2026.0450.119.821.24.323.8
Qwen3-8B-BaseModel=Qwen3-8B-Base2026.0444.931.249.52337.1
Qwen2.5-1.5B-MathModel=Qwen2.5-1.5B-Math2026.0411.712.410.42.79.3