Compare AI Models
Select up to 4 models to compare side by side.
Claude Opus 4.8
Anthropic
|
|
|---|---|
| Overview | |
| Provider | Anthropic |
| DFO score | 68.9 |
| Performance Tier | Specialist |
| Best For | – |
| Released | May 2026 |
| Knowledge Cutoff | – |
| Pricing | |
| Input / 1M tokens | $5.00 |
| Output / 1M tokens | $25.00 |
| Performance | |
| Context Window | 1M |
| Throughput (tok/s) | – |
| Latency (TTFT ms) | – |
| Parameters | – |
| What the boards rank on | |
| Intelligence Index | 41.8 |
| Coding Index | 74.3 |
| Agentic Index | 41.9 |
| Arena creative writing | 1,467 |
| Arena instruction following | 1,491 |
| Benchmarks | |
| Math Index | – |
| MMLU-Pro | – |
| GPQA Diamond | 0.9 |
| LiveCodeBench | – |
| MATH-500 | – |
| AIME '25 | – |
| AIME | – |
| Humanity's Last Exam | 0.5 |
| IFBench | 0.6 |
| Capabilities | |
| Tool Use | Yes |
| Function Calling | Yes |
| Vision | Yes |
| Open Source | No |
| License | – |
Looking for the full rankings? View the AI Model Leaderboard or try the Price Calculator to estimate monthly costs.