Back to Benchmarks

Claude Opus 4.6 (Adaptive Reasoning, Max Effort) vs DeepSeek R1 Distill Qwen 32B

Claude Opus 4.6 (Adaptive Reasoning, Max Effort)

Anthropic

vs

DeepSeek R1 Distill Qwen 32B

DeepSeekvia NextBit

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

Index Scores

53.0
+35.8
Intelligence
17.2
48.1
+48.1
Coding
0.0
0.0
Math
+63.0
63.0

Benchmarks

0.0
MMLU Pro
+73.9
73.9
89.6
+28.1
GPQA
61.5
36.7
+31.2
HLE
5.5
0.0
LiveCode
+27.0
27.0
51.9
+14.3
SciCode
37.6
0.0
MATH-500
+94.1
94.1
0.0
AIME
+68.7
68.7

Speed

36
+12
TPS
24
Shared
Winning delta

crafted by bart stefanski