'/%3E%3Cpath%20fill='%23b2b2b2'%20d='M241%20382q0%2016%2017%2026%2017%2011%2042%2011t42-11q16-11%2017-26V269H241'/%3E%3Cpath%20fill='%239f7e00'%20d='M241%20379q0%2014%208%2023%209%209%2021%209%2014%200%2021-9%209-9%209-23V269h-59'/%3E%3Cpath%20d='M241%20339v-70h59v110q0%2014-9%2023l-6%205v-68h-15v72q-8%200-14-4v-68zm59%2040c0%2022%2015%2032%2029%2032%2021%200%2030-18%2030-32v-40h-59'/%3E%3Cpath%20fill='%239f7e00'%20d='M266%20277v5h2v12h-3v-5h2v-5h-9v5h2v5h-4v9h3v18h-5v10h34v-10h-5v-18h3v-9h-4v-5h2v-5h-9v5h2v5h-3v-12h2v-5zm42%20101q0%2010%206%2017%206%206%2015%207%2010-1%2016-7%206-7%206-17v-29h-43'/%3E%3Ccircle%20fill='%230044ad'%20cx='329.5'%20cy='372'%20r='6'/%3E%3Cellipse%20fill='%230044ad'%20cx='300'%20cy='340'%20rx='16'%20ry='21'/%3E%3C/svg%3E){kind=small}
'%3E%3Cpath%20stroke='%23000'%20stroke-width='4'%20d='m-35-37-13%2020m5%203%2013-20m5%203-13%2020m63%2042%206-9m1-2%206-9m5%203-6%209m-1%202-6%209m5%203%206-9m1-2%206-9m-96%200%2013%2020m5-3-6-9m-1-2-6-9m5-3%2013%2020m63-42-6-9m-1-2-6-9m5-3%2013%2020m5-3-6-9m-1-2-6-9'/%3E%3Ccircle%20r='24'%20fill='%23cd2e3a'/%3E%3Cpath%20fill='%230047a0'%20d='M0%200a12%2012%200%201%201%2020%2013%2024%2024%200%201%201-40-26A12%2012%200%201%200%200%200'/%3E%3C/g%3E%3C/svg%3E){kind=small}
Claude Fable 5.1 and Claude Mythos 5.1 Release Overview
Claude Fable 5.1 and Claude Mythos 5.1 were released as updates to Anthropic’s Mythos-class model line, with Claude Fable 5.1 marking the first Mythos-class update since Fable 5 launched on June 9. Anthropic described the new models as “the world’s most advanced for coding and knowledge work.” Both updates carry the 5.1 version number for Fable and Mythos, making 5.1 the current release identifier for those model families.
Claude Fable 5.1 Benchmark Performance
On the Terminal-Bench-Science 0.1 benchmark, Claude Fable 5.1 scored 52.6%, compared with Fable 5 at 24.7% and Opus 5 at 29.0%. On Terminal-Bench 4.0, Claude Fable 5.1 scored 55.8%, compared with Fable 5 at 42.0% and Opus 5 at 52.3%. Claude Fable 5.1 more than doubled Fable 5’s Terminal-Bench-Science 0.1 score and exceeded Opus 5’s reported scores on these benchmarks. Anthropic published that Fable 5.1 now beats Opus 5 on every benchmark it released.
Mythos 5.1 scored 60.9% on Terminal-Bench-Science 0.1, with Anthropic noting Mythos 5.1 had fewer safeguards and that the score gap reflected tasks the safeguards intercepted and rerouted to Opus 4.8. On Humanity’s Last Exam, Claude Fable 5.1 scored 60.9% without external tools and 65.0% with tools. Anthropic reported that both tool-free and tool-augmented Fable 5.1 results on that test were ahead of Opus 5.
Claude Fable 5.1 Benchmark Performance
On the Terminal-Bench-Science 0.1 benchmark, Claude Fable 5.1 scored 52.6%, compared with Fable 5 at 24.7% and Opus 5 at 29.0%. On Terminal-Bench 4.0, Claude Fable 5.1 scored 55.8%, compared with Fable 5 at 42.0% and Opus 5 at 52.3%. Claude Fable 5.1 more than doubled Fable 5’s Terminal-Bench-Science 0.1 score and beat Opus 5 on these reported benchmarks. Anthropic published that Fable 5.1 now beats Opus 5 on every benchmark it released.
Mythos 5.1 scored 60.9% on Terminal-Bench-Science 0.1, with Anthropic noting Mythos 5.1 had fewer safeguards and that the score gap reflected tasks the safeguards intercepted and rerouted to Opus 4.8. On Humanity’s Last Exam, Claude Fable 5.1 scored 60.9% without external tools and 65.0% with tools. Anthropic reported that both tool-free and tool-augmented Fable 5.1 results on that test were ahead of Opus 5.
Claude Fable 5.1 was released as an update to Anthropic’s Mythos-class model line and represents the first Mythos-class update since Fable 5 launched on June 9. Anthropic reported benchmark results showing Claude Fable 5.1 improved markedly over prior models—more than doubling Fable 5 on Terminal-Bench-Science 0.1 and outperforming Opus 5 across published benchmarks—while Anthropic also presented related Mythos 5.1 and Humanity’s Last Exam outcomes.
