← All comparisons

Qwen3.6 35B A3B (Reasoning) vs DeepSeek V3.1 Terminus (Reasoning)

Alibaba vs DeepSeek — side-by-side benchmark comparison

Qwen3.6 35B A3B (Reasoning)DeepSeek V3.1 Terminus (Reasoning)
Intelligence Index43.533.9
Coding Index35.233.7
Math Index89.7
Output speed (tok/s)159.10.0
Blended price ($/1M)$0.56$1.91
Time to first token (s)1.50s0.00s
aime
aime 2589.7%
artificial analysis coding index35.2033.70
artificial analysis intelligence index43.5033.90
artificial analysis math index89.70
gpqa84.1%79.2%
hle20.2%15.2%
ifbench64.4%57.0%
lcr63.7%65.0%
livecodebench79.8%
math 500
mmlu pro85.1%
scicode35.8%40.6%
tau295.3%37.1%
terminalbench hard34.8%30.3%

Benchmark data from Artificial Analysis.