Claude Opus 4.8
Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents
ECI STANDING#10 of 266
SCORE158.3156.43–160.71 CI
FRONTIER LAGLaunched 2.8 months behindScores about what GPT-5.4 Pro did in March 2026.
SCORES LIKE THESE MODELSGPT-5.6 TerraOpenAI · Jul 2026159.14GPT-5.5OpenAI · Apr 2026159.12GPT-5.4 ProOpenAI · Mar 2026158.95Kimi K3Moonshot · Jul 2026157.63
Full Epoch Capabilities Index ranking ↗From the lab
Launch announcement · May 28, 2026Released Claude Opus 4.8RELEASE DATEMay 28, 2026
WEIGHTSClosed weights
CONTEXT WINDOW1M
MAX OUTPUT128K
REASONINGYes
TOOL CALLINGYes
INPUTStext, image, pdf
OUTPUTStext
Specifications from Models.dev. Availability and limits may differ by provider. Benchmark scores come from Epoch AI under CC BY 4.0.