Model results

ArXivMath

Choose a shared evaluation protocol to compare model scores. Versions, sources and configurations stay separate.

Atlas snapshot captured 10/19/2026, 10:20:28 AM UTC. This is an import timestamp, not the evaluation date. Coverage may be incomplete.

Official source

← All evaluation groups

ArXivMath August 2026

Source: MathArena (reviewed publisher results)
Version: 2026-08-native-harness
Measurement date: Not reported
Metric: % · Higher is better
Evaluation scope: Final-answer correctness; 57 questions; LLM equivalence judge; August 2026 dataset; harness=publisher-selected native harness (exact harness version unspecified); configuration=Kimi K3 (Think); Python and SageMath tools; no internet; budget/time-limit instructions varied across models, see methodology https://matharena.ai/arxiv_august/; 95% CI 12.64%; cost per problem $5.77; result date not supplied; captured 2026-09-17

Fewer than two comparable models. No ranking is assigned. Missing metadata is shown as unreported; matching imported metadata is not independent verification of the protocol.

Kimi K3
moonshotai/kimi-k3-20260715
38.6%
View modelEvidence independent