← All comparisons

DeepSeek V3.1 Terminus (Non-reasoning) vs Qwen2 Instruct 72B

DeepSeek vs Alibaba — side-by-side benchmark comparison

DeepSeek V3.1 Terminus (Non-reasoning)Qwen2 Instruct 72B
Intelligence Index28.511.7
Coding Index31.9
Math Index53.7
Output speed (tok/s)0.00.0
Blended price ($/1M)$0.45$0.00
Time to first token (s)0.00s0.00s
aime14.7%
aime 2553.7%
artificial analysis coding index31.90
artificial analysis intelligence index28.5011.70
artificial analysis math index53.70
gpqa75.1%37.1%
hle8.4%3.7%
ifbench41.2%
lcr43.3%
livecodebench52.9%15.9%
math 50070.1%
mmlu pro83.6%62.2%
scicode32.1%22.9%
tau237.1%
terminalbench hard31.8%

Benchmark data from Artificial Analysis.