← All comparisons

Tiny Aya Global vs Claude 4.5 Sonnet (Reasoning)

Cohere vs Anthropic — side-by-side benchmark comparison

Tiny Aya GlobalClaude 4.5 Sonnet (Reasoning)
Intelligence Index4.743.0
Coding Index1.238.6
Math Index88.0
Output speed (tok/s)124.055.0
Blended price ($/1M)$0.00$6.56
Time to first token (s)0.32s7.02s
aime
aime 2588.0%
artificial analysis coding index1.2038.60
artificial analysis intelligence index4.7043.00
artificial analysis math index88.00
gpqa30.5%83.4%
hle5.2%17.3%
ifbench20.1%57.3%
lcr0.0%65.7%
livecodebench71.4%
math 500
mmlu pro87.5%
scicode3.6%44.7%
tau20.0%78.1%
terminalbench hard0.0%35.6%

Benchmark data from Artificial Analysis.