Back to Benchmarksvs
Claude Opus 4.7 (Adaptive Reasoning, Max Effort) wins 6 of 11
Claude Opus 4.7 (Adaptive Reasoning, Max Effort) vs GLM-5 (Reasoning)
Claude Opus 4.7 (Adaptive Reasoning, Max Effort)
Anthropic
GLM-5 (Reasoning)
Z AIvia Z.AI
Claude Opus 4.7 (Adaptive Reasoning, Max Effort) wins 6 of 11Index Scores
57.3
Intelligence+7.5
49.8
52.5
Coding+8.3
44.2
0.0
Math0.0
Benchmarks
0.0
MMLU Pro0.0
91.4
GPQA+9.4
82.0
39.6
HLE+12.4
27.2
0.0
LiveCode0.0
54.5
SciCode+8.3
46.2
0.0
MATH-5000.0
0.0
AIME0.0
Speed
52
TPS+20
32
Shared
Winning delta
crafted by bart stefanski