Claude Sonnet 5
Claude Sonnet 5 supports coding, agentic workflows, long-context reasoning, computer use, and practical knowledge work.
- 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
1460.9
Overall Rank
#63 / 422
Votes
52,824
Confidence Interval
1456.8 - 1464.9
Category Scores
Coding
#40 / 417
14,005 votes
1519.4
Math
#54 / 405
2,426 votes
1471.7
Longer Query
#46 / 400
24,188 votes
1480.7
Creative Writing
#69 / 420
11,005 votes
1433.4
Instruction Following
#45 / 422
18,596 votes
1466.7
Hard Prompts
#53 / 422
34,684 votes
1489.9
Additional Categories22
Expert
#34 / 372
5,703 votes
1508.9
Industry Mathematical
#44 / 403
2,823 votes
1486.3
French
#46 / 302
1,775 votes
1489.2
Hard Prompts English
#48 / 420
14,533 votes
1493.5
Industry Software And It Services
#50 / 422
20,284 votes
1504.1
Japanese
#50 / 288
793 votes
1441.0
German
#51 / 321
857 votes
1466.3
Industry Life And Physical And Social Science
#52 / 420
8,666 votes
1486.8
Industry Business And Management And Financial Operations
#54 / 415
10,098 votes
1465.7
Industry Writing And Literature And Language
#57 / 421
14,534 votes
1451.6
Russian
#57 / 386
6,224 votes
1466.3
Korean
#58 / 289
855 votes
1422.0
Multi Turn
#58 / 420
8,970 votes
1472.9
Industry Legal And Government
#61 / 394
4,489 votes
1471.2
Industry Medicine And Healthcare
#61 / 392
3,804 votes
1478.8
English
#62 / 422
22,010 votes
1471.1
Exclude Ties
#62 / 422
39,680 votes
1466.2
Non English
#63 / 422
30,810 votes
1447.8
Chinese
#69 / 396
4,024 votes
1495.7
Industry Entertainment And Sports And Media
#70 / 420
13,629 votes
1431.7
Spanish
#70 / 304
1,536 votes
1455.2
Polish
#81 / 243
787 votes
1448.6
Published 2026-11-18 · Matched as Claude Sonnet 5 (High) · CC BY 4.0
LMArena DatasetLeaderboard results
| Benchmark | Score | Rank on NanoGPT |
|---|---|---|
Epoch AI Benchmarking Hub Epoch AI data, CC BY 4.0 · Updated Nov 19, 2026 | ||
Epoch Capabilities Index | 156.9 | #32 of 113 |
FrontierMath v2 (Tiers 1–3) | 65.6% | #37 of 83 |
GPQA Diamond | 90.5% | #41 of 118 |
SimpleQA Verified | 33.7% | #61 of 83 |
FrontierMath v2 (Tier 4) | 29.3% | #35 of 67 |
OTIS Mock AIME 2024–2025 | 94.7% | #45 of 120 |
MirrorCode | 63.3% | #11 of 40 |
Chess Puzzles | 45.0% | #28 of 82 |
Mystery Game Puzzles | 35.0% | #27 of 79 |
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 |