Claude Sonnet 5
- Input
- $2.00/M tok
- Output
- $10/M tok
- Blended
- $4.00/M tok · 3:1
- Speed
- 58tok/s
- Context
- 1Mtokens
- Cost per task
- ~$4.2/taskest.
Introductory $2/$10 price made permanent (Aug 2026).
Rankings
Coding
Mixed#52 / 137rank by quality57.1±5.4quality / 1004/7 benchmarks measuredWriting & chat
Verified#42 / 162rank by quality64.6±4.3quality / 1003/5 benchmarks measuredVision
Mixed#51 / 98rank by quality54.4±4.1quality / 1004/6 benchmarks measuredHard reasoning
Verified#37 / 218rank by quality71.4±3.7quality / 1003/4 benchmarks measuredAgents
Mixed#37 / 187rank by quality64.0±3.8quality / 1005/7 benchmarks measured
Benchmark scores
~ italic, dashed = no published score yet, estimated from related benchmarks.
Coding
SWE-bench Pro (Public)Lab-reported
#10 of 2363.2%
- #1Claude Fable 5.293.0%
- #2Claude Opus 5.589.9%
- #9GPT-5.6 Terra63.4%
- #10Claude Sonnet 563.2%
- #11Nex-N2.5-Pro61.2%
anthropic.com · 2026-06-30
DeepSWE v1.1Estimated
~#36 of 46 (estimated)~56.0%
- #1Gemini 4 Argon78.8%
- #2DeepSeek V4.1 Flash 101777.0%
- #35Qwen3.8 2.4T A95B56.6%
- ~#36Claude Sonnet 5Estimated56.0%
- #36Nex-N2.5-Pro55.8%
No published score — estimated from related benchmarks
Terminal-Bench 4.0Verified
#34 of 10114.1%
- #1Kimi K3.1 Pro67.2%
- #2Claude Sonnet 5.563.6%
- #33GPT-5.514.6%
- #34Claude Sonnet 514.1%
- #34DeepSeek V4 Pro (0813)14.1%
artificialanalysis.ai · 2026-09-24
LiveCodeBenchEstimated
~#12 of 28 (estimated)~78.7%
- #1Qwen3.8-Omni-Flash92.6%
- #2Qwen3.8 Flash-Next91.9%
- #11Gemma 4 31B80.0%
- ~#12Claude Sonnet 5Estimated78.7%
- #12gpt-oss-20b77.7%
No published score — estimated from related benchmarks
SciCodeVerified
#30 of 11854.3%
- #1Claude Fable 5.267.7%
- #2Claude Opus 5.566.9%
- #29GPT-6 Luna54.6%
- #30Claude Sonnet 554.3%
- #31Mistral Large 454.2%
artificialanalysis.ai · 2026-09-24
AA Coding Agent IndexEstimated
~#21 of 26 (estimated)~40.0
- #1Claude Opus 5.561.7
- #2Claude Opus 559.7
- #20Kimi K341.4
- ~#21Claude Sonnet 5Estimated40.0
- #21Qwen3.8 Max (0902)39.2
No published score — estimated from related benchmarks
Writing & chat
IFBenchEstimated
~#39 of 140 (estimated)~69.3%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #38Xing4.0-29B-A4B69.7%
- ~#39Claude Sonnet 5Estimated69.3%
- #39Apriel-v1.6-15B-Thinker69.1%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Verified
#19 of 561447 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #18DeepSeek V4 Pro (0813)1448
- #19Claude Sonnet 51447
- #19Grok 4.61447
lmarena.ai · 2026-09-24
LMArena Text (Elo)Verified
#19 of 561461 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #18DeepSeek V4 Pro (0813)1463
- #19Claude Sonnet 51461
- #20GPT-6 Sol1457
lmarena.ai · 2026-09-24
#14 of 251794 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #13Muse Glimmer1798
- #14Claude Sonnet 51794
- #15Gemini 3.8 Flash1748
eqbench.com · 2026-09-24
Vision
MMMU-ProVerified
#26 of 8777.3%
- #1Claude Opus 5.587.7%
- #2GPT-6 Astra86.9%
- #25Grok 4.778.2%
- #26Claude Sonnet 577.3%
- #26Qwen3.5 397B A17B77.3%
artificialanalysis.ai · 2026-09-24
CharXiv ReasoningLab-reported
#10 of 1177.0%
- #1Gemini 3.8 Flash86.2%
- #2Kimi K384.8%
- #9Inkling78.1%
- #10Claude Sonnet 577.0%
- #11Gemini 3.5 Flash-Lite74.5%
www-cdn.anthropic.com · 2026-06-30
OmniDocBench v1.5Estimated
~#4 of 8 (estimated)~85.5%
- #1MiniMax-M391.6%
- #2Kimi K391.1%
- #2Qwen3.8 27B91.1%
- ~#4Claude Sonnet 5Estimated85.5%
- #4Gemini 3.1 Pro85.3%
No published score — estimated from related benchmarks
GDP.pdf (AA)Verified
#28 of 4713.2%
- #1Muse Wonder Full32.6%
- #2GPT-6 Astra31.0%
- #27GPT-5.4 mini13.4%
- #28Claude Sonnet 513.2%
- #29DeepSeek V4.1 Flash12.8%
artificialanalysis.ai · 2026-09-24
ChartographyVerified
#18 of 2416.6%
- #1Claude Fable 5.273.4%
- #2GPT-6 Astra71.0%
- #17Muse Glimmer17.2%
- #18Claude Sonnet 516.6%
- #19GLM-5.3 Flash16.3%
surgehq.ai · 2026-09-24
Hard reasoning
GPQA DiamondVerified
#26 of 19291.1%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #25GLM-5.3 Flash91.2%
- #26Claude Sonnet 591.1%
- #27Qwen3.8-Omni-Flash91.0%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#32 of 19841.3%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #31GLM-5.342.3%
- #32Claude Sonnet 541.3%
- #33DeepSeek V4 Pro (0813)41.0%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#8 of 34 (estimated)~94.1%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #7Nova 2.0 Lite94.3%
- ~#8Claude Sonnet 5Estimated94.1%
- #8gpt-oss-120b93.4%
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Estimated
~#19 of 120 (estimated)~88.7%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #18MiniMax-M388.9%
- ~#19Claude Sonnet 5Estimated88.7%
- #19Qwen3.5 Omni Plus88.3%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~last of 5 (estimated)below measured range (<47.5%)
No published score — estimated from related benchmarks
BrowseCompLab-reported
#9 of 2184.7%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #8Gemini 3.1 Pro85.9%
- #9Claude Sonnet 584.7%
- #10GPT-5.584.4%
www-cdn.anthropic.com · 2026-06-30
GDPval-AA (Elo)Verified
#22 of 911449 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #21GPT-6 Sol1487
- #22Claude Sonnet 51449
- #23DeepSeek V4 Pro (0813)1441
artificialanalysis.ai · 2026-09-24
AutomationBench-AAVerified
#30 of 8436.5%
- #1Claude Fable 5.276.4%
- #2Muse Wonder Full71.3%
- #29K2 Horizon 375B A23B37.2%
- #30Claude Sonnet 536.5%
- #31GPT-5.5 Instant (June 2026)36.4%
artificialanalysis.ai · 2026-09-24