Balanced Claude model for coding, analysis, agent workflows, and cost control
Specification
most-agreed values
Context
1M
Max output
128K
Released
2026-02-17
Knowledge cutoff
2025-08-31
Retires
—
Open weights
no
Input
text, image, pdf
Output
text
Price
US dollars per million tokens · most-agreed
Input
$3.196
Output
$15.94
Cache read
$0.32
Cache write
$3.999
Quality
8 benchmarks · 2 sources
Composite
64th
percentile of 334 scored models
Rank
121 / 334
±0.08 sd
Evidence
8 × 2
3 or more benchmarks, from 2 or more sources
Effort range
9.3
points between effort settings
reasoning59th3/4 bench
math84th3/7 bench
knowledge38th1/1 bench
general32nd1/1 bench
By reasoning effort
every setting placed on the same scale as the leaderboard
| Setting | Composite | Benchmarks behind it |
|---|---|---|
| 32k | 83rd | 3 |
| 16k | 83rd | 2 |
| medium | 75th | 3 |
| high | 63rd | 4 |
| max | 57th | 4 |
| auto | 42nd | 1 |
| low | 42nd | 1 |
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| FrontierMath-v1 | 56.2 ±13.3 | 16k · 2 runs | Epoch AI | 2026-02-22 |
| GPQA diamond | 87.4 ±2.0 | 32k | Epoch AI | 2026-02-20 |
| ↳ | 83.3 ±2.7 | high | Epoch AI | 2026-07-13 |
| ↳ | 83.3 ±2.7 | medium | Epoch AI | 2026-07-13 |
| ↳ | 78.8 ±2.9 | max | Epoch AI | 2026-08-06 |
| Settings differ by 8.6 points on this benchmark. | ||||
| OTIS Mock AIME 2024-2025 | 85.8 ±4.5 | 32k | Epoch AI | 2026-02-20 |
| ↳ | 82.2 ±5.8 | medium | Epoch AI | 2026-07-13 |
| ↳ | 75.6 ±6.5 | high | Epoch AI | 2026-07-13 |
| ↳ | 71.1 ±6.8 | max | Epoch AI | 2026-08-06 |
| Settings differ by 14.7 points on this benchmark. | ||||
| FrontierMath-Tier-4-2025-07-01 | 4.2 ±0.0 | 16k · 2 runs | Epoch AI | 2026-02-22 |
| LiveBench | 73.4 | auto · 23 runs | LiveBench | 2026-06-25 |
| Mystery Game Puzzles | 16.0 ±3.7 | low | Epoch AI | 2026-08-06 |
| SimpleQA Verified | 35.5 ±1.5 | high | Epoch AI | 2026-08-10 |
| ↳ | 32.8 ±1.5 | max | Epoch AI | 2026-08-27 |
| Settings differ by 2.7 points on this benchmark. | ||||
| Chess Puzzles | 13.0 ±3.4 | 32k | Epoch AI | 2026-02-20 |
| ↳ | 8.0 ±2.7 | medium | Epoch AI | 2026-07-13 |
| ↳ | 5.0 ±2.2 | high | Epoch AI | 2026-07-13 |
| ↳ | 3.0 ±1.7 | max | Epoch AI | 2026-08-06 |
| Settings differ by 10.0 points on this benchmark. | ||||
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 1 host
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| cortecs | $3.196 | $15.94 | $0.32 | $3.999 | 1M | 128K | — |
Other listings of this model
this page is one of them
The corpus files Claude Sonnet 4.6 under several keys. This page is the claude-4-6-sonnet listing. The full record — every host, every price and every benchmark score — is on the main Claude Sonnet 4.6 page.
More from Anthropic
most-hosted first