Claude Opus 5 Benchmarks, Pricing & Rankings
Anthropic · 2026-05-12 · Closed · Current
Snapshot 2026-10-14 · updated weekly
Claude Opus 5 ranks #8 of 42 on the AMR leaderboard.
Claude Opus 5 benchmark scores
| GPQA Diamond | 90.7% | |
| MMLU-Pro | 87.4% | |
| SWE-Bench Verified | 75.6% | |
| AIME 2025 | 89.9% | |
| LiveCodeBench v6 | 79.1% | |
| Arena Elo | 1447 |
Claude Opus 5 price, speed & context
Input price
$6
per 1M tokens
Output price
$30
per 1M tokens
Speed
96
tok/s
Context
400K
tokens
About Claude Opus 5
Claude Opus 5 was the top coding model of early 2026 and remains the strongest SWE-Bench performer in the Anthropic lineup before Opus 5.5.
Models around Claude Opus 5 in the rankings
More Anthropic models
Claude Opus 5 FAQ
Where does Claude Opus 5 rank?
Claude Opus 5 ranks #8 of 42 tracked AI models on the AMR aggregate as of October 2026, with an aggregate score of 92.6. Its strongest dimension is GPQA Diamond at 90.7%.
How much does Claude Opus 5 cost?
Claude Opus 5 costs $6 per million input tokens and $30 per million output tokens on the standard API. At a typical 1:3 input/output agent workload, that blends to roughly $24.00 per million tokens.
What is the Claude Opus 5 context window?
Claude Opus 5 supports a 400K token context window and generates at a median 96 output tokens per second. That context fits roughly 267 standard documents in a single prompt.
Is Claude Opus 5 open source?
No — Claude Opus 5 is a closed model available only through Anthropic’s official API and authorized cloud partners.
What is better than Claude Opus 5?
Gemini 4 Argon ranks one place higher at #7 with an AMR score of 93.2. Claude Opus 5 still wins 1 of the tracked dimensions head-to-head — check the comparison table to see exactly which.