Frontier Log

Benchmark · Active

GraphWalks

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

020406080100Oct 2025Jan 2026Apr 2026Jul 202691.1%Mythos 590.7%GPT-5.6 Sol76.9%GPT-5.6 Terra85.9%Opus 4.873.7%GPT-5.576.91%Opus 4.785.7%Mythos Preview62.5%GPT-5.4020406080100Oct 2025Jan 2026Apr 2026Jul 202691.1%Mythos 590.7%GPT-5.6 Sol76.9%GPT-5.6 Terra73.7%GPT-5.585.7%Mythos Preview

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 202691.1%Claude Fable 5 and Claude Mythos 5 System CardCorroborated The same number is printed in 1 other lab document: 15 trials
GPT-5.6 Sol9 Jul 202690.7%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 202685.9%Claude Opus 4.8 System CardCorroborated The same number is printed in 2 other lab documents: 1 2max effort · 5 trials
Claude Mythos Preview7 Apr 202685.7%Claude Fable 5 and Claude Mythos 5 System CardCorroborated The same number is printed in 1 other lab document: 15 trials · reported later
GPT-5.6 Luna9 Jul 202681.3%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 4.716 Apr 202676.91%Claude Opus 4.7 System CardCorroborated The same number is printed in 2 other lab documents: 1 25 trials
GPT-5.6 Terra9 Jul 202676.9%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 Sonnet 4.617 Feb 202674.5%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 202672.8%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
GPT-5.523 Apr 202673.7%Introducing GPT-5.5Corroborated The same number is printed in 3 other lab documents: 1 2 3Our capture
GPT-5.45 Mar 202662.5%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 Opus 4.65 Feb 202661.5%Claude Opus 4.6 System CardCorroborated The same number is printed in 1 other lab document: 164K extended thinking · 5 trials
Claude Opus 4.65 Feb 202661.1%Claude Opus 4.6 System CardCorroborated The same number is printed in 2 other lab documents: 1 2max effort · 5 trials · another report, not charted
Claude Sonnet 4.529 Sep 202544.9%Claude Opus 4.6 System CardCorroborated The same number is printed in 1 other lab document: 164K extended thinking · reported later

All benchmarks