Claude Opus 4.5 (batch)
Anthropic · released Nov 24, 2025
Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...
Specification
- Context window
- 200K
- Max output
- 64K
- Knowledge cutoff
- Not stated
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 1
- Moderated
- Yes
Intelligence
35.6
82th percentile
Coding
—
Coding Index
Agentic
—
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
- MMLU-Pro88.9%
- τ²-bench (Telecom)86.3%
- GPQA Diamond81.0%
- LiveCodeBench73.8%
- AA-LCR (long context)67.3%
- AIME 202562.7%
- SciCode47.0%
- IFBench43.0%
- Terminal-Bench Hard40.9%
- Humanity's Last Exam13.2%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| MMLU-Pro | 88.9% |
| τ²-bench (Telecom) | 86.3% |
| GPQA Diamond | 81.0% |
| LiveCodeBench | 73.8% |
| AA-LCR (long context) | 67.3% |
| AIME 2025 | 62.7% |
| SciCode | 47.0% |
| IFBench | 43.0% |
| Terminal-Bench Hard | 40.9% |
| Humanity's Last Exam | 13.2% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- Kimi K2.5Moonshot AI36.0
- Claude Opus 4.5 (batch)Anthropic35.6
- Claude Opus 4.5Anthropic35.6
- GPT-5.1-CodexOpenAI35.6
- GLM 5V TurboZ.ai35.3
- GPT-5OpenAI35.3
- Qwen3.5-27BQwen34.6
- M2.5MiniMax34.5
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Kimi K2.5 | 36.0 |
| Claude Opus 4.5 (batch) | 35.6 |
| Claude Opus 4.5 | 35.6 |
| GPT-5.1-Codex | 35.6 |
| GLM 5V Turbo | 35.3 |
| GPT-5 | 35.3 |
| Qwen3.5-27B | 34.6 |
| M2.5 | 34.5 |
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
- 1,274
- Win rate
- 58.5%
- Strongest at
- UI components
- Tournaments
- 2,047
Elo by category
Dot position on a 1,225–1,275 scale · Elo has no meaningful zero
- 1,274
- 1,271
- 1,270
- 1,270
- 1,268
- 1,227
Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.
View as table
| Category | Elo | Win rate |
|---|---|---|
| UI components | 1274 | 58.5% |
| Game development | 1271 | 59.4% |
| Websites | 1270 | 59.8% |
| Data visualisation | 1270 | 58.5% |
| 3D scenes | 1268 | 58.5% |
| SVG | 1227 | 58.7% |