Noometry

Anthropic, proprietary

Claude Sonnet 5

Claude Sonnet 5 by Anthropic ranks 29th of 354 ranked models on the Noometry Index as of October 2026, with a score of 54.6. Its strongest category is agentic & tool use, where it ranks 18th. API pricing starts at $2 per million input tokens and $10 per million output tokens, with a 1M-token context window.

Last verified

Noometry rank
#29 of 354
Index score
54.6
Evidence
Confirmed 51 results
Provider
Anthropic
Released
June 29, 2026
Weights
Proprietary
Reasoning
Yes
Context window
1M
Max output
128K
Input price
$2 / M
Output price
$10 / M
Blended price
$4 / M
Output speed
Not measured
Value
#167 of 219
Knowledge cutoff
January 2026
Input
text, image, pdf

Category scores

Each category score combines every public result we have in that category.

  1. Coding 55.5
  2. Agentic & Tool Use 42.8
  3. Reasoning 49.1
  4. Math 66.2
  5. Knowledge 55.6
  6. Multimodal 42.4
  7. Multilingual 53.8
  8. Instruction Following 76.3
  9. Long Context 44.8
  10. Writing & Preference 69.2
CategoryScoreRankResults
Coding55.5#268
Agentic & Tool Use42.8#182
Reasoning49.1#399
Math66.2#275
Knowledge55.6#473
Multimodal42.4#312
Multilingual53.8#551
Instruction Following76.3#411
Long Context44.8#551
Writing & Preference69.2#255

Strengths and weaknesses

Categories where Claude Sonnet 5 places highest and lowest among the models ranked in each, with its score against that category's median.

Strongest categories

CategoryScorevs medianRank
Coding55.5+16.8#26 of 340, top 8%
Writing & Preference69.2+15.5#25 of 312, top 9%
Math66.2+29.6#27 of 327, top 9%

Weakest categories

CategoryScorevs medianRank
Multimodal42.4+3.8#31 of 128, top 25%
Long Context44.8+3.8#55 of 296, top 19%
Multilingual53.8+6.4#55 of 297, top 19%

Closest competitors

The models ranked just above and below Claude Sonnet 5. When scores are this close, price and speed are often the better way to choose.

ModelRankScoreBlended $/MSpeed
Grok 4.5#2555.0$34Compare
GLM-5.3#2654.8$2.15—Compare
Muse Spark 1.3#2754.8$2—Compare
Gemini 3 Pro#2854.8—1Compare
GPT-5.6 Luna#3054.6$0.4512Compare
DeepSeek V4 Pro#3154.3$0.9916Compare
Gemini 3.5 Flash#3254.2$3.38—Compare
Gemini 3.6 Flash#3354.1$1.50—Compare

Sponsored placements are available on pages like this one. Advertise on Noometry

Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

Coding

BenchmarkScorePositionSettingSourceDate
DeepSWE48.2%highEpoch AI
DeepSWE30.5%lowEpoch AI
DeepSWE53.8%#20 of 29, top 69%maxEpoch AI
DeepSWE39.8%mediumEpoch AI
DeepSWE49.7%xhighEpoch AI
FrontierCode42.7%#16 of 37, top 44%Epoch AI
CursorBench30.8%highEpoch AI
CursorBench24.1%lowEpoch AI
CursorBench34.1%#14 of 14, top 100%maxEpoch AI
CursorBench28%mediumEpoch AI
CursorBench32%xhighEpoch AI
LMArena WebDev1541#37 of 113, top 33%highLMArena2026-10-08
SciCode54.3%#28 of 121, top 24%highEpoch AI
SciCode50.1%lowEpoch AI
SciCode53.6%maxEpoch AI
SciCode51.6%mediumEpoch AI
SciCode54.1%xhighEpoch AI
GSO37.3%#9 of 31, top 30%Epoch AI
WeirdML68.8%#20 of 119, top 17%highEpoch AI
LMArena Coding1483#42 of 294, top 15%highLMArena2026-10-08
ALE-Bench1,463#18 of 105, top 18%highEpoch AI

Agentic & Tool Use

BenchmarkScorePositionSettingSourceDate
APEX-Agents54.5%#20 of 49, top 41%Epoch AI
GBAEval65.3%#5 of 23, top 22%Epoch AI
LMArena Search1194#17 of 32, top 54%LMArena2026-08-24
Vending-Bench 26,378#17 of 60, top 29%Epoch AI

Reasoning

BenchmarkScorePositionSettingSourceDate
SimpleBench60.6%#24 of 77, top 32%Epoch AI
NYT Connections (extended)75.1%#42 of 91, top 47%high reasoningLech Mazur benchmarks
CritPt1.1%highEpoch AI
CritPt4.6%lowEpoch AI
CritPt16.9%#33 of 134, top 25%maxEpoch AI
CritPt8.6%mediumEpoch AI
CritPt15.4%xhighEpoch AI
Chess Puzzles16%maxEpoch AI2026-06-30
Chess Puzzles35%#29 of 129, top 23%xhighEpoch AI2026-06-30
LMArena Hard Prompts1461#47 of 297, top 16%highLMArena2026-10-08
Mystery Game Puzzles16%Epoch AI2026-08-06
Mystery Game Puzzles35%#18 of 74, top 25%maxEpoch AI2026-07-28
DTBench84.5%highEpoch AI
DTBench73.6%lowEpoch AI
DTBench92.5%#27 of 151, top 18%maxEpoch AI
DTBench79.2%mediumEpoch AI
DTBench89.5%xhighEpoch AI
LMCA50%#21 of 125, top 17%highEpoch AI
LMCA49.6%lowEpoch AI
LMCA49.3%maxEpoch AI
LMCA49.7%mediumEpoch AI
LMCA48.8%xhighEpoch AI
Surface Evolver Bench60%#10 of 25, top 40%mediumEpoch AI
Bench to the Future 30.14#4 of 10, top 40%xhighEpoch AI
Epoch Capabilities Index156.21#26 of 213, top 13%Epoch AI2026-06-30
ForecastBench61.1#16 of 72, top 23%16KEpoch AI

Math

BenchmarkScorePositionSettingSourceDate
FrontierMath (Tiers 1-3)65.6%#31 of 81, top 39%maxEpoch AI2026-06-30
FrontierMath Tier 429.3%#29 of 63, top 47%maxEpoch AI2026-06-30
OTIS Mock AIME 2024-202580%maxEpoch AI2026-08-06
OTIS Mock AIME 2024-202594.7%#36 of 173, top 21%xhighEpoch AI2026-07-01
ProofBench77%#12 of 77, top 16%maxEpoch AI
LMArena Math1467#43 of 285, top 16%highLMArena2026-10-08

Knowledge

BenchmarkScorePositionSettingSourceDate
GPQA Diamond80.3%maxEpoch AI2026-08-06
GPQA Diamond90.5%#35 of 186, top 19%xhighEpoch AI2026-07-01
SimpleQA Verified33.7%#52 of 77, top 68%maxEpoch AI2026-08-27
SimpleQA Verified32.9%xhighEpoch AI2026-08-27
LMArena Expert1490#31 of 273, top 12%highLMArena2026-10-08

Multimodal

BenchmarkScorePositionSettingSourceDate
LMArena Vision1274#34 of 122, top 28%highLMArena2026-10-09
Blueprint-Bench 224.9%#21 of 31, top 68%Epoch AI
LMArena Document1466#14 of 38, top 37%highLMArena2026-09-13

Multilingual

BenchmarkScorePositionSettingSourceDate
LMArena Non-English1431#56 of 297, top 19%highLMArena2026-10-08
LMArena Chinese1477#67 of 285, top 24%highLMArena2026-10-08
LMArena French1460#50 of 223, top 23%highLMArena2026-10-08
LMArena German1440#55 of 231, top 24%highLMArena2026-10-08
LMArena Japanese1422#38 of 211, top 19%highLMArena2026-10-08
LMArena Korean1411#43 of 213, top 21%highLMArena2026-10-08
LMArena Russian1451#42 of 283, top 15%highLMArena2026-10-08
LMArena Spanish1437#70 of 226, top 31%highLMArena2026-10-08

Instruction Following

BenchmarkScorePositionSettingSourceDate
LMArena Instruction Following1452#39 of 298, top 14%highLMArena2026-10-08

Long Context

BenchmarkScorePositionSettingSourceDate
LMArena Longer Query1463#37 of 291, top 13%highLMArena2026-10-08

Writing & Preference

BenchmarkScorePositionSettingSourceDate
LMArena Text1442#57 of 297, top 20%highLMArena2026-10-08
LMArena Creative Writing1416#57 of 295, top 20%highLMArena2026-10-08
EQ-Bench Creative Writing1794#25 of 115, top 22%EQ-Bench
EQ-Bench 41236#10 of 28, top 36%EQ-Bench
LMArena Multi-Turn1454#48 of 295, top 17%highLMArena2026-10-08

API pricing by provider

RouteInput $/MOutput $/MCached input $/MChecked
anthropic$2$10$0.202026-10-10
azure$2$10$0.202026-10-10
bedrock$2$10$0.202026-10-10
openrouter$2$10$0.202026-10-10
vertex$2$10$0.202026-10-10

All Anthropic API prices → Estimate your cost →

Compare Claude Sonnet 5

Other Anthropic models

Frequently asked questions

How good is Claude Sonnet 5?

Claude Sonnet 5 by Anthropic ranks 29th of 354 ranked models on the Noometry Index as of October 2026, with a score of 54.6. Its strongest category is agentic & tool use, where it ranks 18th. API pricing starts at $2 per million input tokens and $10 per million output tokens, with a 1M-token context window.

How much does Claude Sonnet 5 cost?

Claude Sonnet 5 costs $2 per million input tokens and $10 per million output tokens on Anthropic's own API, with cached input at $0.20.

What is Claude Sonnet 5's context window?

Claude Sonnet 5 accepts up to 1M tokens of input and can write up to 128K tokens in one response.

Is Claude Sonnet 5 open source?

No. Claude Sonnet 5 is proprietary and available only through Anthropic's API and partner platforms.

What are Claude Sonnet 5's strengths and weaknesses?

Relative to other ranked models, Claude Sonnet 5 places best in coding, writing & preference, math and lowest in multimodal, long context, multilingual.

What is Claude Sonnet 5 best at?

Its best category is agentic & tool use, where it ranks 18th on Noometry.