Frontier Log

Benchmark · Active

AutomationBench, no release named

Created by Zapier, 20 Apr 2026 · Higher is better · Website

01020304050Apr 2026Jul 2026Oct 202631.4%Fable 5.118.1%GPT-5.6 Sol26.0%Opus 513.5%Sonnet 517.4%Fable 515.5%Opus 4.812.9%GPT-5.501020304050Apr 2026Jul 2026Oct 202631.4%Fable 5.126.0%Opus 513.5%Sonnet 517.4%Fable 515.5%Opus 4.8

Results

ModelScoreSource
Claude Fable 5.11 Sep 2026 · Anthropic31.4%Introducing Claude Fable 5.1 and Claude Mythos 5.1Corroborated The same number is printed in 3 other lab documents: 1 2 3Run by Zapier · max effort; with production safeguards; set named in the Claude Fable 5.1 system card, which prints the same figureOur capture
Claude Opus 524 Jul 2026 · Anthropic26.0%Introducing Claude Opus 5Corroborated The same number is printed in 1 other lab document: 1Run by Zapier · max effort; set named in the Claude Opus 5 system card, which prints the same figureSource image
Claude Opus 524 Jul 2026 · Anthropic24%Claude Opus 5 System CardChecked A person checked this number against its source on 20 Oct 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Run by Zapier · medium effort; another report, not charted
GPT-5.6 Sol9 Jul 2026 · OpenAI18.1%GPT-5.6: Frontier intelligence that scales with your ambitionCorroborated The same number is printed in 2 other lab documents: 1 2Run by ZapierOur capture
Claude Fable 59 Jun 2026 · Anthropic17.4%Claude Fable 5 and Claude Mythos 5 System CardCorroborated The same number is printed in 2 other lab documents: 1 2Run by Zapier · max effortOur capture
Claude Fable 59 Jun 2026 · Anthropic17.1%Introducing Claude Fable 5.1 and Claude Mythos 5.1Corroborated The same number is printed in 1 other lab document: 1Run by Zapier · tasks blocked by safeguards scored zero; set named in the Claude Fable 5.1 system card, which prints 17.05; reported later; another report, not chartedOur capture
Claude Opus 4.828 May 2026 · Anthropic15.5%Claude Opus 4.8 System CardCorroborated The same number is printed in 2 other lab documents: 1 2Run by Zapier · max effortOur capture
Claude Opus 4.828 May 2026 · Anthropic17.0%Introducing Claude Opus 5Corroborated The same number is printed in 1 other lab document: 1Run by Zapier · max effort; set named in the Claude Opus 5 system card, which prints the same figure; reported later; another report, not chartedSource image
GPT-5.6 Terra9 Jul 2026 · OpenAI15.2%GPT-5.6: Frontier intelligence that scales with your ambitionChecked A person checked this number against its source on 26 Oct 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Run by ZapierOur capture
GPT-5.6 Luna9 Jul 2026 · OpenAI14.9%GPT-5.6: Frontier intelligence that scales with your ambitionChecked A person checked this number against its source on 26 Oct 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Run by ZapierOur capture
Claude Sonnet 530 Jun 2026 · Anthropic13.5%Claude Sonnet 5 System CardChecked A person checked this number against its source on 20 Oct 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Run by Zapier · max effortOur capture
GPT-5.523 Apr 2026 · OpenAI12.9%GPT-5.6: Frontier intelligence that scales with your ambitionCorroborated The same number is printed in 1 other lab document: 1Run by Zapier · reported laterOur capture

All benchmarks