← All comparisons

Tri-21B-think Preview vs Claude 3.5 Sonnet (Oct '24)

Trillion Labs vs Anthropic — side-by-side benchmark comparison

Tri-21B-think PreviewClaude 3.5 Sonnet (Oct '24)
Intelligence Index20.015.9
Coding Index7.430.2
Math Index
Output speed (tok/s)0.00.0
Blended price ($/1M)$0.00$6.56
Time to first token (s)0.00s0.00s
aime15.7%
aime 25
artificial analysis coding index7.4030.20
artificial analysis intelligence index20.0015.90
artificial analysis math index
gpqa53.8%59.9%
hle5.7%3.9%
ifbench47.1%
lcr14.7%
livecodebench38.1%
math 50077.1%
mmlu pro77.2%
scicode17.8%36.6%
tau293.3%
terminalbench hard2.3%

Benchmark data from Artificial Analysis.