#6
Claude Opus 4.8
Anthropic · Proprietary · Reasoning · 1M context
78/ 100 composite
Released 2026-05-28
Benchmark Scores by Category
Coding
69.1
Knowledge
87.6
Reasoning
77.3
Agentic
83.2
Math
67.1
Multimodal
90.2
Scores based on weighted benchmarks: SWE-bench, LiveCodeBench (Coding); HLE, MMLU-Pro (Knowledge); ARC-AGI-2, LongBench v2 (Reasoning); Terminal-Bench, BrowseComp (Agentic); FrontierMath, AIME (Math).
API Pricing
Input
$5
per 1M tokens
Output
$25
per 1M tokens
Value Score
3.1
score per $1 output
Estimate Your Costs
Use our cost calculators to estimate monthly spend based on your specific workload: