Back to Benchmarks

Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) vs GPT-4.1 nano

Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)

Anthropic

vs

GPT-4.1 nano

OpenAI

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

Index Scores

51.7
+38.7
Intelligence
13.0
50.9
+39.7
Coding
11.2
0.0
Math
+24.0
24.0

Benchmarks

0.0
MMLU Pro
+65.7
65.7
87.5
+36.3
GPQA
51.2
30.0
+26.1
HLE
3.9
0.0
LiveCode
+32.6
32.6
46.8
+20.9
SciCode
25.9
0.0
MATH-500
+84.8
84.8
0.0
AIME
+23.7
23.7

Speed

42
+7
TPS
35
Shared
Winning delta

crafted by bart stefanski