Anthropic's flagship for agentic coding and long business workflows. It comes close to Fable 5 at half the price.
Released July 24, 2026
GDPval-AA v2
Real paid work from 44 different jobs, such as law, nursing, and software. Judges compare two answers side by side without knowing which model wrote them, and the winner gains rating points. A typical human expert scores 1000, so a higher number means the work was picked over a human more often.
Independently measured by Artificial Analysis.
SWE-bench Verified
Hands the AI bugs from actual software projects and counts how many it fixes. Like a coding job interview, but with real work.
Independently measured by vals.ai.
Terminal-Bench 2.1
Puts the AI in front of a computer terminal and asks it to finish multi-step tasks on its own. Measures how good an "AI agent" it is.
Independently measured by vals.ai.
GPQA Diamond
PhD-level science questions written so you cannot just Google the answer. Tests whether the model can reason about hard science.
Independently measured by vals.ai.
Humanity's Last Exam
PhD-level questions across many subjects. Tests deep reasoning on the hardest questions humans can ask.
Independently measured by Artificial Analysis.
Artificial Analysis Intelligence Index
A frequently refreshed overall score made from nine modern tests: real work, tool use, terminal tasks, science, hard questions, and long-context reasoning. It is a scorecard rather than a percent correct.
Independently measured by Artificial Analysis.
Opus 5 is the strongest coding model tracked here, and it tops the SWE-Bench Verified leaderboard. It costs half of what Fable 5 costs, so it is the better default for everyday engineering work. The 1M token context lets you hand it a whole codebase at once.
Opus 5 scores higher on coding benchmarks at half the price. Fable 5 still leads on the hardest reasoning tasks.
Opus 5 leads on SWE-Bench Verified. Sol edges ahead on Terminal-Bench.
Anthropic ships a flagship built for agentic coding and business workflows at $5/$25 per million tokens, which is half the price of Fable 5. It has a 1M token context window, and it now leads the SWE-Bench Verified leaderboard at 97%.