Claude Opus 5.5 Benchmark

Your browser does not support the video tag. 0:00 Gemini 4 Argon vs Claude Opus 5.5: price and independent test results Argon vs Opus 5.5 in 30 Seconds Price: Argon’s $2 / $10 is a launch promotion. Google’s own footnote says the price moves to $4 / $20 once it ends, exactly what Opus 5.5 costs. No end date yet. Independent benchmarks: On the Artificial Analysis Intelligence Index, Opus 5.5 scores 58 and Argon 53. Cost per task is $1.99 for Argon at promo pricing versus $5.98 for Opus. Hallucinations: Argon’s hallucination rate is 15%, Opus 5.5’s is 59%. Argon says “I don’t know” far more often, while Opus knows more but also guesses when it shouldn’t. Coding: Opus leads Terminal-Bench 4.0 in both Google’s table and the independent run. Argon leads on workflow automation. Access: Opus 5.5 is available today. Argon is limited to selected cyber defense teams. When Google announced Gemini 4 Argon on September 30, the headline number was simple: a frontier model at half the price of Claude Opus 5.5. A day later, two things are clearer. That price has an expiry date, and the first independent benchmark run puts the two models in a different order than Google’s own chart. ...

Summary: Claude Opus 5.5 in 30 Seconds Released 22 September 2026, available the same day on every platform Anthropic ships to. $4 in / $20 out per million tokens, against $5 / $25 on Opus 5. Cache reads drop from $0.50 to $0.20. Anthropic measures a 40% lower total cost on typical workloads and 30%+ faster output generation. Model ID is claude-opus-5-5. Four breaking API changes land with it. Sonnet 5.5 and Haiku 5.5 follow in the coming weeks. What Opus 5.5 Costs The headline price is 20% under Opus 5, but the number that moves most bills is the cache read rate. On agentic and coding work, cache reads are where the majority of spend lands, and they got 60% cheaper. ...