Back to Benchmarks

Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) vs GPT-4o mini

Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)

Anthropic

vs

GPT-4o mini

OpenAI

Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) wins 6 of 11

Index Scores

51.7
+39.1
Intelligence
12.6
50.9
+50.9
Coding
0.0
0.0
Math
+14.7
14.7

Benchmarks

0.0
MMLU Pro
+64.8
64.8
87.5
+44.9
GPQA
42.6
30.0
+26.0
HLE
4.0
0.0
LiveCode
+23.4
23.4
46.8
+23.9
SciCode
22.9
0.0
MATH-500
+78.9
78.9
0.0
AIME
+11.7
11.7

Speed

42
+12
TPS
30
Shared
Winning delta

crafted by bart stefanski