Claude 4.6 Opus Thinking
Claude Opus 4.6 with adaptive thinking enabled (default effort: high).
- Reasoning
- Vision
- Native PDF input
- Tool Calling
- Structured Output
Added Feb 5, 2026
Pricing
Auto routing · per 1M tokens- Input
- $5.00
- Output
- $25.00
- Cache read
- $0.50
Specifications
- Context window
- 1M
- Max output
- 128K
Benchmarks
Benchmarks
Sourced from Vectara.
Hallucination Rate
12.2%
Factual Consistency
87.8%
Answer Rate
99.8%
Avg Summary Length
Average generated summary length
137.6
Last updated 2026-10-22 · Matched as anthropic/claude-opus-4-6
Vectara LeaderboardLeaderboard results
These leaderboards tested Claude 4.6 Opus, another version of this model.
| Benchmark | Score | Rank on NanoGPT |
|---|---|---|
Epoch AI Benchmarking Hub Epoch AI data, CC BY 4.0 · Updated Nov 12, 2026 | ||
Epoch Capabilities Index | 156.3 | #36 of 115 |
FrontierMath v2 (Tiers 1–3) | 66.0% | #35 of 83 |
SWE-bench Verified | 78.7% | #3 of 28 |
GPQA Diamond | 90.5% | #39 of 119 |
SimpleQA Verified | 47.0% | #36 of 82 |
FrontierMath v2 (Tier 4) | 26.8% | #38 of 67 |
OTIS Mock AIME 2024–2025 | 94.4% | #44 of 121 |
MirrorCode | 33.3% | #26 of 39 |
Chess Puzzles | 21.0% | #59 of 82 |
Mystery Game Puzzles | 25.0% | #40 of 77 |
Sierra τ-bench tau2-bench data, MIT · Updated Aug 4, 2026 | ||
τ³-Banking | 27.3% | #13 of 18 |
EQ-Bench 4 | 1210 | #17 of 31 |
Creative Writing v3 | 1810 | #25 of 96 |
Longform Writing | 77.7 | #25 of 97 |
EQ-Bench 3 | 1712 | #4 of 49 |
UGI Leaderboard UGI Leaderboard data, Apache-2.0 · Updated Oct 16, 2026 | ||
UGI Score | 60.4 | #5 of 149 |
UGI Willingness | 3.2 | #72 of 149 |
UGI Writing | 70.9 | #7 of 149 |
Filtered and ranked to models on NanoGPT.
Providers
Auto routing is available for this model. Explicit provider selection is not available.
| Cache write /M | ||||||
|---|---|---|---|---|---|---|
 Recommended | $5.00 | $25.00 | $0.50 | $6.25 | N/A | N/A |
