Frontier Log

Benchmark · Active

GraphWalks

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

020406080100Oct 2025Jan 2026Apr 2026Jul 202699.96%Mythos 590.1%GPT-5.593.57%Opus 4.782.8%GPT-5.497.9%Sonnet 4.695.4%Opus 4.681.0%Sonnet 4.5020406080100Oct 2025Jan 2026Apr 2026Jul 202699.96%Mythos 590.1%GPT-5.582.8%GPT-5.497.9%Sonnet 4.695.4%Opus 4.6

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 202699.96%Claude Fable 5 and Claude Mythos 5 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
Claude Mythos Preview7 Apr 202699.9%Claude Fable 5 and Claude Mythos 5 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 · reported later
Claude Opus 4.828 May 202699.3%Claude Opus 4.8 System CardCorroborated The same number is printed in 1 other lab document: 1max effort · 5 trials
Claude Sonnet 4.617 Feb 202697.9%Claude Sonnet 4.6 System CardChecked 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.max effort · 5 trials
Claude Sonnet 4.617 Feb 202696.9%Claude Sonnet 4.6 System CardChecked 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.64K extended thinking · 5 trials · another report, not charted
Claude Opus 4.65 Feb 202695.4%Claude Opus 4.6 System CardCorroborated The same number is printed in 2 other lab documents: 1 2max effort · 5 trials
Claude Opus 4.65 Feb 202695.1%Claude Opus 4.6 System CardCorroborated The same number is printed in 1 other lab document: 164K extended thinking · 5 trials · another report, not charted
Claude Opus 4.716 Apr 202693.57%Claude Opus 4.7 System CardCorroborated The same number is printed in 2 other lab documents: 1 25 trials
GPT-5.523 Apr 202690.1%Introducing GPT-5.5Corroborated The same number is printed in 2 other lab documents: 1 2Our capture
GPT-5.45 Mar 202682.8%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
Claude Sonnet 4.529 Sep 202581.0%Claude Opus 4.6 System CardCorroborated The same number is printed in 1 other lab document: 164K extended thinking · reported later

All benchmarks