Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Math on GSM8K (Accuracy)
Loading...
96.06
Accuracy
LLaDA-2.0-flash
76.8928
81.8689
86.845
91.8211
Jun 1, 2026
Accuracy
Updated 1d ago
Evaluation Results
Method
Method
Links
Accuracy
LLaDA-2.0-flash
Params=100B-A5B, Sampl...
2026.06
96.06
LLaDA-2.0-mini
Params=16B-A1B, Sampli...
2026.06
94.24
FLARE-9B
Params=9B, Sampling mo...
2026.06
93.33
FLARE-9B
Params=9B, Sampling mo...
2026.06
93.1
FLARE
Params=4B, Sampling mo...
2026.06
91.58
SDAR 30B-A3B
Params=30B-A3B, Sampli...
2026.06
91.4
SDAR
Params=8B, Sampling mo...
2026.06
91.3
FLARE
Params=4B, Sampling mo...
2026.06
91.05
Mercury-2
Params=Commercial, Sam...
2026.06
90.62
SDAR
Params=4B, Sampling mo...
2026.06
89.9
Qwen3.5-9B
Params=9B, Sampling mo...
2026.06
89.16
Qwen3.5
Params=4B, Sampling mo...
2026.06
89.16
FLARE
Params=2B, Sampling mo...
2026.06
84.46
FLARE
Params=2B, Sampling mo...
2026.06
82.79
SDAR
Params=1.7B, Sampling...
2026.06
80.1
Qwen3.5
Params=2B, Sampling mo...
2026.06
77.63
Feedback
Search any
task
Search any
task