Back to Benchmarksvs
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) wins 6 of 11
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) vs GLM-5 (Reasoning)
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)
Anthropic
GLM-5 (Reasoning)
Z AIvia Z.AI
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) wins 6 of 11Index Scores
51.7
Intelligence+1.9
49.8
50.9
Coding+6.7
44.2
0.0
Math0.0
Benchmarks
0.0
MMLU Pro0.0
87.5
GPQA+5.5
82.0
30.0
HLE+2.8
27.2
0.0
LiveCode0.0
46.8
SciCode+0.6
46.2
0.0
MATH-5000.0
0.0
AIME0.0
Speed
42
TPS+10
32
Shared
Winning delta
crafted by bart stefanski