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.
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=Codex 0.153.3; configuration=GPT-6 Sol (max); reasoning effort max; Python and SageMath tools; no internet; budget/time-limit instructions varied across models, see methodology https://matharena.ai/arxiv_august/; 95% CI 6.63%; cost per problem $4.82; model configuration https://matharena.ai/models/openai_gpt_6_sol; result date not supplied; captured 2026-10-15; publisher flags model release after competition release; publisher model endpoint openai/gpt-6-sol; publisher does not expose a dated provider revision
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.
GPT-6 Sol
openai/gpt-6-sol-20260922
92.98%
View modelEvidence independent