Claude Opus 4.8
Claude Opus 4.8 is an API-only (closed weights) language model from Anthropic, released May 28, 2026. The context window is 1M tokens. On the Epoch Capabilities Index it scores 159.9, rank 21 of 256 rated models. API price: $5 input / $25 output per million tokens.
Check it against your own PC →
Lab
Anthropic
Released
May 28, 2026
Weights
API-only (closed weights)
Parameters
–
Context
1M
Price / M tokens
$5 / $25 in / out
Epoch ECI
159.9 #21
Strengths by category
ModelTape's 0–100 fit on Epoch AI benchmark results.
| Category | Score | Based on |
|---|---|---|
| Reasoning | 26.2 | Chess Puzzles, SimpleBench, Mystery Game Puzzles |
| Math | 66.0 | ProofBench, OTIS Mock AIME 2024-2025, FrontierMath-Tiers-1-3-v2-Private, FrontierMath-Tier-4-v2-Private |
| Coding | 67.0 | GSO-Bench, MirrorCode, DeepSWE |
| Agent | 28.2 | Remote Labor Index, OSWorld 2.0 |
| Knowledge | 77.0 | GPQA diamond, SimpleQA Verified |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| OTIS Mock AIME | 98.3% |
| GPQA Diamond | 91.7% |
| FrontierMath (Tiers 1–3) | 84.2% |
| ProofBench | 69.0% |
| MirrorCode | 65.6% |
| DeepSWE | 59.0% |
| SimpleBench | 57.8% |
| FrontierMath-Tier-4-v2-Private | 56.1% |
| SimpleQA Verified | 53.0% |
| Chess Puzzles | 49.5% |
| GSO-Bench | 47.1% |
| Mystery Game Puzzles | 29.5% |
| EBR-bench | 28.6% |
| OSWorld 2.0 | 20.6% |
| Furniture Assembly | 17.9% |
| Remote Labor Index | 8.3% |
Links
Announcement · Epoch AI benchmarks
Models with a similar score
GPT-6 Sol · GPT-5.6 Sol · GPT-5.5 Pro · Muse Wonder · Kimi K3.1 Pro · GPT-5.6 Terra · Claude Haiku 5.5 · GPT-5.4 Pro
More from Anthropic
Claude Fable 5.2 · Claude Haiku 5.5 · Claude Sonnet 5.5 · Claude Opus 5.5 · Claude Fable 5.1 · Claude Opus 5 · Claude Sonnet 5 · Claude Fable 5