Back to Benchmarks

Qwen3.5 397B A17B (Reasoning) vs DeepSeek R1 Distill Llama 70B

Qwen3.5 397B A17B (Reasoning)

Alibaba

vs

DeepSeek R1 Distill Llama 70B

DeepSeekvia DeepInfra

Qwen3.5 397B A17B (Reasoning) wins 6 of 11

Index Scores

45.0
+29.0
Intelligence
16.0
41.3
+29.9
Coding
11.4
0.0
Math
+53.7
53.7

Benchmarks

0.0
MMLU Pro
+79.5
79.5
89.3
+49.1
GPQA
40.2
27.3
+21.2
HLE
6.1
0.0
LiveCode
+26.6
26.6
42.0
+10.8
SciCode
31.2
0.0
MATH-500
+93.5
93.5
0.0
AIME
+67.0
67.0

Speed

53
+11
TPS
42
Shared
Winning delta

crafted by bart stefanski