Claude Opus 4.8 (batch)
Anthropic · released May 27, 2026
Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...
Specification
- Context window
- 1M
- Max output
- 128K
- Knowledge cutoff
- Not stated
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 1
- Moderated
- Yes
Intelligence
57.3
98th percentile
Coding
74.3
Coding Index
Agentic
49.4
Agentic Index
Output speed
—
Median across providers
Latency
—
Time to first token
Cost per task
$1.13
Estimated
Benchmarks
Where the score comes from
The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.
Evaluation scores
Percentage correct · higher is better
- τ²-bench (Telecom)94.4%
- GPQA Diamond92.0%
- AA-LCR (long context)73.0%
- IFBench62.2%
- Terminal-Bench Hard58.3%
- SciCode53.5%
- Humanity's Last Exam48.7%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| τ²-bench (Telecom) | 94.4% |
| GPQA Diamond | 92.0% |
| AA-LCR (long context) | 73.0% |
| IFBench | 62.2% |
| Terminal-Bench Hard | 58.3% |
| SciCode | 53.5% |
| Humanity's Last Exam | 48.7% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- Qwen3.8 MaxQwen58.1
- Claude Opus 4.8 (batch)Anthropic57.3
- Claude Opus 4.8Anthropic57.3
- Muse Spark 1.2Meta56.8
- GPT-5.6 TerraOpenAI56.6
- GPT-5.5OpenAI56.3
- Grok 4.5xAI55.8
- Claude Sonnet 5Anthropic55.3
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Qwen3.8 Max | 58.1 |
| Claude Opus 4.8 (batch) | 57.3 |
| Claude Opus 4.8 | 57.3 |
| Muse Spark 1.2 | 56.8 |
| GPT-5.6 Terra | 56.6 |
| GPT-5.5 | 56.3 |
| Grok 4.5 | 55.8 |
| Claude Sonnet 5 | 55.3 |
Percentile among all indexed models
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- $2.5
- Output / 1M tokens
- $12.5
- Cached input / 1M
- $0.25
- Blended 3:1
- $5
One task, estimated
$1.13
- Input tokens
- 50,000
- Output tokens
- 80,000
- Profile
- Reasoning
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).
Serving providers
Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.
Arena
Head-to-head generation quality
Elo from pairwise judgements, broken out by the kind of thing the model was asked to build.
- Overall Elo
- 1,285
- Win rate
- 54.5%
- Strongest at
- Game development
- Tournaments
- 1,981
Elo by category
Dot position on a 1,225–1,300 scale · Elo has no meaningful zero
- 1,285
- 1,282
- 1,275
- 1,270
- 1,265
- 1,225
- 1,285
- 1,255
Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.
View as table
| Category | Elo | Win rate |
|---|---|---|
| Game development | 1285 | 54.5% |
| UI components | 1282 | 54.7% |
| 3D scenes | 1275 | 53.3% |
| Websites | 1270 | 54.1% |
| Data visualisation | 1265 | 54.6% |
| SVG | 1225 | 53.4% |
| Full-stack apps | 1285 | 62.2% |
| Mobile apps | 1255 | 57.5% |