Frontier Log

Benchmark · Active

GraphWalks

Created by OpenAI, 12 Apr 2025 · Higher is better · Website

020406080Apr 2026Jul 202679.4%Mythos 577.1%GPT-5.6 Sol51.2%GPT-5.6 Luna71.2%GPT-5.6 Terra68.1%Opus 4.845.4%GPT-5.540.3%Opus 4.774.3%Mythos Preview020406080Apr 2026Jul 202679.4%Mythos 577.1%GPT-5.6 Sol51.2%GPT-5.6 Luna71.2%GPT-5.6 Terra68.1%Opus 4.8

Settings and run setups

DomainTask setProviders
BFSUp to 128KOpenAIGoogle
BFS256K + 1M problemsOpenAIAnthropicGoogle
BFS256K problems onlyOpenAIAnthropic
BFS1M problems onlyOpenAIAnthropic
ParentsUp to 128KOpenAI
Parents256K + 1M problemsOpenAIAnthropic
Parents256K problems onlyOpenAIAnthropic
Parents1M problems onlyOpenAIAnthropic

Download image

Results

ModelScoreSource
Claude Mythos 59 Jun 202679.4%Claude Fable 5 and Claude Mythos 5 System CardCorroborated The same number is printed in 1 other lab document: 15 trials · run past the API's 1M-token limit
GPT-5.6 Sol9 Jul 202677.1%GPT-5.6: Frontier intelligence that scales with your ambitionChecked A person checked this number against its source on 11 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Our capture
Claude Mythos Preview7 Apr 202674.3%Claude Fable 5 and Claude Mythos 5 System CardCorroborated The same number is printed in 1 other lab document: 15 trials · run past the API's 1M-token limit · reported later
GPT-5.6 Terra9 Jul 202671.2%GPT-5.6: Frontier intelligence that scales with your ambitionChecked A person checked this number against its source on 11 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Our capture
Claude Opus 4.828 May 202668.1%Claude Opus 4.8 System CardCorroborated The same number is printed in 2 other lab documents: 1 2max effort · 5 trials · run past the API's 1M-token limit
GPT-5.6 Luna9 Jul 202651.2%GPT-5.6: Frontier intelligence that scales with your ambitionChecked A person checked this number against its source on 11 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Our capture
GPT-5.523 Apr 202645.4%Introducing GPT-5.5Corroborated The same number is printed in 3 other lab documents: 1 2 3Our capture
Claude Opus 4.716 Apr 202640.3%Claude Opus 4.8 System CardChecked A person checked this number against its source on 10 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.5 trials · run past the API's 1M-token limit · reported later
Claude Opus 4.65 Feb 202616.3%Claude Opus 4.8 System CardChecked A person checked this number against its source on 10 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.5 trials · run past the API's 1M-token limit · reported later
GPT-5.45 Mar 20269.4%Introducing GPT-5.5Checked A person checked this number against its source on 11 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.reported laterOur capture

All benchmarks