Claude Sonnet 5 Thinking
Claude Sonnet 5 with adaptive thinking enabled for complex coding, planning, and agentic work.
- Reasoning
- Vision
- Native PDF input
- Tool Calling
- Structured Output
Added Jun 30, 2026
Pricing
Auto routing · per 1M tokens- Input
- $2.00
- Output
- $10.00
- Cache read
- $0.20
Specifications
- Context window
- 1M
- Max output
- 128K
Benchmarks
Benchmarks
Sourced from LMArena.
Arena Score
1460.8
Overall Rank
#62 / 421
Votes
52,963
Confidence Interval
1456.8 - 1464.9
Category Scores
Coding
#39 / 416
14,060 votes
1519.8
Math
#50 / 404
2,423 votes
1472.2
Longer Query
#47 / 399
24,283 votes
1480.7
Creative Writing
#68 / 419
11,021 votes
1433.6
Instruction Following
#44 / 421
18,652 votes
1466.6
Hard Prompts
#52 / 421
34,792 votes
1489.9
Additional Categories22
Expert
#33 / 371
5,729 votes
1508.9
French
#43 / 301
1,783 votes
1488.9
Industry Mathematical
#43 / 402
2,836 votes
1486.5
Hard Prompts English
#47 / 419
14,564 votes
1493.4
Industry Software And It Services
#49 / 421
20,363 votes
1504.5
Industry Business And Management And Financial Operations
#51 / 414
10,114 votes
1465.8
Industry Life And Physical And Social Science
#51 / 419
8,702 votes
1486.8
German
#52 / 320
858 votes
1466.0
Japanese
#52 / 288
809 votes
1439.9
Russian
#54 / 385
6,244 votes
1466.8
Industry Writing And Literature And Language
#56 / 420
14,561 votes
1451.8
Multi Turn
#57 / 419
8,981 votes
1473.0
Industry Legal And Government
#58 / 393
4,495 votes
1471.5
Korean
#58 / 289
856 votes
1422.0
Industry Medicine And Healthcare
#60 / 391
3,814 votes
1479.3
English
#61 / 421
22,039 votes
1471.1
Exclude Ties
#61 / 421
39,779 votes
1466.2
Non English
#62 / 421
30,920 votes
1447.8
Chinese
#66 / 395
4,028 votes
1496.6
Industry Entertainment And Sports And Media
#69 / 419
13,679 votes
1432.2
Spanish
#69 / 304
1,540 votes
1454.5
Polish
#80 / 243
786 votes
1448.9
Published 2026-11-11 · Matched as Claude Sonnet 5 (High) · CC BY 4.0
LMArena DatasetLeaderboard results
These leaderboards tested Claude Sonnet 5, another version of this model.
| Benchmark | Score | Rank on NanoGPT |
|---|---|---|
Epoch AI Benchmarking Hub Epoch AI data, CC BY 4.0 · Updated Nov 18, 2026 | ||
Epoch Capabilities Index | 156.9 | #32 of 113 |
FrontierMath v2 (Tiers 1–3) | 65.6% | #36 of 82 |
GPQA Diamond | 90.5% | #40 of 117 |
SimpleQA Verified | 33.7% | #60 of 82 |
FrontierMath v2 (Tier 4) | 29.3% | #34 of 66 |
OTIS Mock AIME 2024–2025 | 94.7% | #44 of 119 |
MirrorCode | 63.3% | #11 of 40 |
Chess Puzzles | 45.0% | #27 of 81 |
Mystery Game Puzzles | 35.0% | #26 of 78 |
EQ-Bench 4 | 1221 | #14 of 31 |
Creative Writing v3 | 1798 | #27 of 91 |
Longform Writing | 78.3 | #20 of 93 |
UGI Leaderboard UGI Leaderboard data, Apache-2.0 · Updated Oct 16, 2026 | ||
UGI Score | 45.3 | #54 of 125 |
UGI Willingness | 2.2 | #83 of 125 |
UGI Writing | 62.7 | #29 of 125 |
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 | $2.00 | $10.00 | $0.20 | $2.50 | N/A | N/A |