Claude Opus 4.6 (batch)
Anthropic · released Feb 4, 2026
Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...
Specification
- Context window
- 1M
- Max output
- 128K
- Knowledge cutoff
- Not stated
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 1
- Moderated
- Yes
Intelligence
38.8
86th 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
- τ²-bench (Telecom)84.8%
- GPQA Diamond84.0%
- AA-LCR (long context)62.3%
- Terminal-Bench Hard48.5%
- SciCode45.7%
- IFBench44.6%
- Humanity's Last Exam19.1%
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) | 84.8% |
| GPQA Diamond | 84.0% |
| AA-LCR (long context) | 62.3% |
| Terminal-Bench Hard | 48.5% |
| SciCode | 45.7% |
| IFBench | 44.6% |
| Humanity's Last Exam | 19.1% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- Qwen3.7 PlusQwen39.4
- GLM 5 TurboZ.ai39.1
- M2.7MiniMax38.9
- Claude Opus 4.6 (batch)Anthropic38.8
- Claude Opus 4.6Anthropic38.8
- MiMo-V2.5Xiaomi38.0
- Grok 4.20xAI38.0
- Grok 4.3xAI37.9
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Qwen3.7 Plus | 39.4 |
| GLM 5 Turbo | 39.1 |
| M2.7 | 38.9 |
| Claude Opus 4.6 (batch) | 38.8 |
| Claude Opus 4.6 | 38.8 |
| MiMo-V2.5 | 38.0 |
| Grok 4.20 | 38.0 |
| Grok 4.3 | 37.9 |
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
- 1,329
- Win rate
- 62.5%
- Strongest at
- 3D scenes
- Tournaments
- 5,816
Elo by category
Dot position on a 1,250–1,350 scale · Elo has no meaningful zero
- 1,329
- 1,320
- 1,320
- 1,315
- 1,310
- 1,275
- 1,279
- 1,262
Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.
View as table
| Category | Elo | Win rate |
|---|---|---|
| 3D scenes | 1329 | 62.5% |
| UI components | 1320 | 60.0% |
| Game development | 1320 | 61.2% |
| Websites | 1315 | 61.4% |
| Data visualisation | 1310 | 58.7% |
| SVG | 1275 | 61.1% |
| Mobile apps | 1279 | 64.8% |
| Full-stack apps | 1262 | 68.5% |