Best AI for Mathematics
Sally has three brothers. Each brother has two sisters. That trap, plus a from-memory estimate of what GPT-3 cost to train.
5 challenges20 models
How Mathematics rankings are computed
20 models tested across 5 mathematics challenges.Composite score: 30% Rival Index, 20% task coverage, 20% challenge-scoped duel performance, 15% recency, 15% tier. Deduplicated by product line. Kimi K3 leads at 81.8/100. Drawn from Rival's open dataset of 21,000+ human preference votes.
Rival's Pick#12 Rival IndexAnthropic flagship
Too close to callComposite scores combine task evidence, Rival Index, recency, and model tier. Rival’s Pick is a separate editorial recommendation. How ranking works
Claude Fable 5
anthropic
$10.00·$50.00
82Composite
Kimi K3
moonshotai
$3.00·$15.00
82Composite
Qwen3.7 Max
qwen
$2.50·$7.50
81Composite
Head-to-Head
Full Rankings
20 models#
Model
Coverage
Index
Price
Composite
Challenges5
Related