Bb5a31f81ClaimOpenAI's GPT-6.1 Terra model operated three times faster than both Sol and Astra on Agent's Last ExamAgreeDisagree
Bb5a31f81ClaimOpenAI's GPT-6.1 Terra scored 48 on the AA Coding Agent Index, ranking behind GLM 5.3 and ahead of DeepSeek v4.1 FlashAgreeDisagree
Bb5a31f81ClaimOpenAI disproved the exponential time hypothesis in computational complexity theoryAgreeDisagree
Bb5a31f81ClaimOpenAI's GPT-6.1 Terra model completed benchmark tasks on Agent's Last Exam at half the cost of Sol and one-tenth the cost of AstraAgreeDisagree
Bb5a31f81ClaimOpenAI artificial intelligence models proved a 1991 local smoothing conjecture as a general case across all dimensionsAgreeDisagree
Bb5a31f81ClaimArtificial Analysis recorded a score of 47 for GPT-6.1 Terra, four points lower than GPT-6.1 Sol and two points higher than Grok 4.7 on maximum settingsAgreeDisagree
Bb5a31f81ClaimAnthropic conducts early access evaluation testing with external API customers including CognitionAgreeDisagree
Bb5a31f81ClaimAnthropic engineering teams manage API integration experiences while product management focuses on commercial impact and safety requirementsAgreeDisagree
Bb5a31f81ClaimLarge language models can generate evaluation benchmarks, write comments, and output comparative ratings such as Elo scores for agent harnessesAgreeDisagree
Bb5a31f81ClaimAnthropic conducts internal testing referred to as ant-fooding on candidate model variants prior to cutting versions for external API customersAgreeDisagree
Bb5a31f81ClaimApproaching harness engineering like research involves establishing upfront targets, formalizing evaluations, and systematically diagnosing failure modesAgreeDisagree
Bb5a31f81ClaimAnthropic verified the Rust rewrite of the Messages API by routing shadow traffic and comparing system outputs against the Python implementationAgreeDisagree
Bb5a31f81ClaimIn Leash Bio's benchmark experiments, certain language model agents selected molecules that contradicted the agents' own stated structure-activity relationship hypothesesAgreeDisagree
Bb5a31f81ClaimClaude Sonnet 5.5 achieved strong performance on Leash Bio's chemical exploration benchmarkAgreeDisagree
Bb5a31f81ClaimOn the GDPVAL AA benchmark for agentic white-collar work, Kimi K3.1 ranked behind Opus 5.5 and ahead of Fable 5.1AgreeDisagree
Bb5a31f81ClaimClaude Sonnet 5 exhibited high operational costs and low performance on Leash Bio's chemical exploration benchmarkAgreeDisagree
Bb5a31f81ClaimLeash Bio evaluates agent exploration strategies on structure-activity relationship tasks within fully pre-measured chemical landscapesAgreeDisagree
Bb5a31f81ClaimSolve 6.1 demonstrated high performance on Leash Bio's chemical exploration benchmarkAgreeDisagree
Bb5a31f81ClaimLeash Bio generated approximately 90,000 agent rollouts within its pre-measured chemical sandbox environmentAgreeDisagree