Frontier Log

Benchmark · Active

Chartography

Created by Surge AI, 16 Jul 2026 · Higher is better · Website

020406080Oct 2025Jan 2026Apr 2026Jul 2026Oct 202672.5%Gemini 4 Carbon64.4%Opus 5.546.4%Haiku 5.561.6%Sonnet 5.542.6%Fable 5.129.6%Opus 516.0%Sonnet 517.0%Opus 4.8020406080Oct 2025Jan 2026Apr 2026Jul 2026Oct 202672.5%Gemini 4 Carbon46.4%Haiku 5.542.6%Fable 5.129.6%Opus 516.0%Sonnet 5

Results

ModelScoreSourceSource check
Gemini 4 Carbon28 Oct 2026 · Google72.5%Gemini 4 Carbon: our next frontier modelrun by Surge AI, from its public leaderboardSource image
Claude Haiku 5.57 Oct 2026 · Anthropic46.4%Introducing Claude Haiku 5.5
CorroboratedThe same number is printed in 1 other lab document: 1
Gemini 4 Argon30 Sep 2026 · Google71.6%Gemini 4 Argon: our next era of frontier intelligencerun by Surge AI, from its public leaderboardSource image
CorroboratedThe same number is printed in 1 other lab document: 1
Claude Sonnet 5.528 Sep 2026 · Anthropic61.6%Introducing Claude Sonnet 5.5
CorroboratedThe same number is printed in 3 other lab documents: 1 2 3
Claude Opus 5.522 Sep 2026 · Anthropic64.4%Claude Opus 5.5 System Cardadaptive thinking, max effort; average of 5 runs; Gemini 3.5 Flash grader
CorroboratedThe same number is printed in 3 other lab documents: 1 2 3
Claude Fable 5.11 Sep 2026 · Anthropic42.6%Claude Fable 5.1 and Claude Mythos 5.1 System Cardadaptive thinking, max effort; average of 5 runs
Claude Fable 5.11 Sep 2026 · Anthropic44.8%Claude Opus 5.5 System Cardadaptive thinking, max effort; average of 5 runs; Gemini 3.5 Flash grader; reported later; another report, not charted
CorroboratedThe same number is printed in 1 other lab document: 1
Claude Opus 524 Jul 2026 · Anthropic29.6%Claude Opus 5 System Cardadaptive thinking, max effort; average of 5 runs
CorroboratedThe same number is printed in 1 other lab document: 1
Claude Opus 524 Jul 2026 · Anthropic29.8%Claude Opus 5.5 System Cardadaptive thinking, max effort; average of 5 runs; Gemini 3.5 Flash grader; reported later; another report, not charted
Claude Sonnet 530 Jun 2026 · Anthropic16.0%Claude Opus 5 System Cardadaptive thinking, max effort; average of 5 runs; reported later
Claude Sonnet 530 Jun 2026 · Anthropic15.6%Introducing Claude Sonnet 5.5reported later; another report, not charted
CorroboratedThe same number is printed in 1 other lab document: 1
Claude Fable 59 Jun 2026 · Anthropic36.6%Claude Fable 5.1 and Claude Mythos 5.1 System Cardadaptive thinking, max effort; average of 5 runs; reported later
Claude Mythos 59 Jun 2026 · Anthropic36.0%Claude Opus 5 System Cardadaptive thinking, max effort; average of 5 runs; reported later
Claude Opus 4.828 May 2026 · Anthropic17.0%Claude Opus 5 System Cardadaptive thinking, max effort; average of 5 runs; reported later
Claude Haiku 4.515 Oct 2025 · Anthropic6.4%Introducing Claude Haiku 5.5reported later
CorroboratedThe same number is printed in 1 other lab document: 1

All benchmarks