Model results

FrontierCode

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

FrontierCode

Source: Cognition via Epoch AI
Version: Not reported
Measurement date: Not reported
Metric: % · Higher is better
Evaluation scope: Harness codex · Aggregation Mean@5 · effort unspecified · result date not supplied

Positions are withheld because at least one result lacks explicit independent provenance or a documented evaluation scope. Missing metadata is shown as unreported; matching imported metadata is not independent verification of the protocol.

GPT-5.6 Sol
openai/gpt-5.6-sol-20260709
47.5%
View modelEvidence aggregated
GPT-5.5
openai/gpt-5.5-20260423
43%
View modelEvidence aggregated
GPT-5.6 Terra
openai/gpt-5.6-terra-20260709
41.3%
View modelEvidence aggregated
GPT-5.6 Luna
openai/gpt-5.6-luna-20260709
39.8%
View modelEvidence aggregated
GPT-5.4 Mini
openai/gpt-5.4-mini-20260317
27%
View modelEvidence aggregated