Model comparison

Claude Sonnet 5 vs DeepSeek-R1

Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 42.3 on the Noometry Index. DeepSeek-R1 costs 4.4× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.

Last verified October 10, 2026. 27 shared benchmarks.

Claude Sonnet 5 Anthropic

54.6

Rank #29 Confirmed

DeepSeek-R1

DeepSeek

42.3

Rank #115 Confirmed

Summary

They share 27 benchmarks with published results for both. Claude Sonnet 5 scores higher in 8 categories and DeepSeek-R1 in 1 category; 8 gaps are clear of the uncertainty.
The widest gap is in reasoning, where Claude Sonnet 5 leads 49.1 to 18.6.
The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 94.7% for Claude Sonnet 5 and 66.4% for DeepSeek-R1.
DeepSeek-R1 is cheaper at $0.50 / $2.15 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.
Claude Sonnet 5 accepts more context: 1M tokens versus 164K.

Side by side

Claude Sonnet 5 and DeepSeek-R1 specifications
	Claude Sonnet 5	DeepSeek-R1
Provider	Anthropic	DeepSeek
Noometry Index	54.6	42.3
Released	2026-06-29	2025-01-20
Weights	Proprietary	Proprietary
Context window	1M	164K
Max output	128K	64K
Input $ / M tokens	$2	$0.50
Output $ / M tokens	$10	$2.15
Results tracked	51	52

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

Category by category

Coding Claude Sonnet 5 leads

Claude Sonnet 5: 55.5 (#26), DeepSeek-R1: 46.3 (#68)

Coding benchmarks
Benchmark	Claude Sonnet 5	DeepSeek-R1
SciCode	54.3%	35.7%
WeirdML	68.8%	41.6%
LMArena Coding	1483	1427
ALE-Bench	1,463	804.12
DeepSWE	53.8%	—
FrontierCode	42.7%	—
Aider Polyglot	—	71.4%
CursorBench	34.1%	—
LMArena WebDev	1541	—
GSO	37.3%	—
LiveBench Coding	—	66.7%
AlgoTune	—	1.7

Agentic & Tool Use Claude Sonnet 5 leads

Claude Sonnet 5: 42.8 (#18), DeepSeek-R1: 30.7 (#75)

Agentic & Tool Use benchmarks
Benchmark	Claude Sonnet 5	DeepSeek-R1
APEX-Agents	54.5%	—
DeepResearch Bench	—	35.1%
BALROG	—	34.9%
GBAEval	65.3%	—
LMArena Search	1194	—
METR Time Horizons	—	53.8%
Vending-Bench 2	6,378	—

Reasoning Claude Sonnet 5 leads

Claude Sonnet 5: 49.1 (#39), DeepSeek-R1: 18.6 (#278)

Reasoning benchmarks
Benchmark	Claude Sonnet 5	DeepSeek-R1
SimpleBench	60.6%	40.8%
CritPt	16.9%	1.1%
LMArena Hard Prompts	1461	1416
Epoch Capabilities Index	156.21	141.29
ForecastBench	61.1	60
ARC-AGI-2	—	1.3%
Kagi LLM Benchmark	—	69.4%
NYT Connections (extended)	75.1%	—
ARC-AGI-1	—	21.2%
Chess Puzzles	35%	—
LiveBench Reasoning	—	83.2%
Mystery Game Puzzles	35%	—
DTBench	92.5%	—
LiveBench Data Analysis	—	69.8%
LMCA	50%	—
Surface Evolver Bench	60%	—
Bench to the Future 3	0.14	—
LiveBench	—	71.6%

Math Claude Sonnet 5 leads

Claude Sonnet 5: 66.2 (#27), DeepSeek-R1: 43.8 (#79)

Math benchmarks
Benchmark	Claude Sonnet 5	DeepSeek-R1
OTIS Mock AIME 2024-2025	94.7%	66.4%
LMArena Math	1467	1400
FrontierMath (Tiers 1-3)	65.6%	—
FrontierMath Tier 4	29.3%	—
ProofBench	77%	—
Omni-MATH	—	42.4%
LiveBench Math	—	80.7%
MATH Level 5	—	96.6%

Knowledge Claude Sonnet 5 leads

Claude Sonnet 5: 55.6 (#47), DeepSeek-R1: 44.5 (#87)

Knowledge benchmarks
Benchmark	Claude Sonnet 5	DeepSeek-R1
GPQA Diamond	90.5%	76.3%
LMArena Expert	1490	1394
SimpleQA Verified	33.7%	—
MMLU-Pro	—	79.3%
Confabulations	—	12.7%
Vectara Hallucination Rate	—	11.3%
GPQA (HELM)	—	66.6%

Multimodal Not comparable

Claude Sonnet 5: 42.4 (#31), DeepSeek-R1: —

Multimodal benchmarks
Benchmark	Claude Sonnet 5	DeepSeek-R1
LMArena Vision	1274	—
Blueprint-Bench 2	24.9%	—
LMArena Document	1466	—

Multilingual Claude Sonnet 5 leads

Claude Sonnet 5: 53.8 (#55), DeepSeek-R1: 52.4 (#85)

Multilingual benchmarks
Benchmark	Claude Sonnet 5	DeepSeek-R1
LMArena Non-English	1431	1412
LMArena Chinese	1477	1442
LMArena French	1460	1417
LMArena German	1440	1404
LMArena Japanese	1422	1391
LMArena Korean	1411	1360
LMArena Russian	1451	1423
LMArena Spanish	1437	1411

Instruction Following Claude Sonnet 5 leads

Claude Sonnet 5: 76.3 (#41), DeepSeek-R1: 72.0 (#143)

Instruction Following benchmarks
Benchmark	Claude Sonnet 5	DeepSeek-R1
LMArena Instruction Following	1452	1382
LiveBench Instruction Following	—	80.5%
IFEval	—	78.4%

Long Context Too close to call

Claude Sonnet 5: 44.8 (#55), DeepSeek-R1: 45.4 (#36)

Long Context benchmarks
Benchmark	Claude Sonnet 5	DeepSeek-R1
LMArena Longer Query	1463	1391
Fiction.LiveBench	—	75%

Writing & Preference Claude Sonnet 5 leads

Claude Sonnet 5: 69.2 (#25), DeepSeek-R1: 61.4 (#88)

Writing & Preference benchmarks
Benchmark	Claude Sonnet 5	DeepSeek-R1
LMArena Text	1442	1428
LMArena Creative Writing	1416	1405
EQ-Bench Creative Writing	1794	1500
LMArena Multi-Turn	1454	1405
Short-Story Creative Writing	—	83%
WildBench	—	82.8%
EQ-Bench 4	1236	—
LiveBench Language	—	48.5%

Frequently asked questions

Is Claude Sonnet 5 better than DeepSeek-R1?

Which is cheaper, Claude Sonnet 5 or DeepSeek-R1?

DeepSeek-R1 is cheaper. It lists at $0.50 per million input tokens and $2.15 per million output tokens; Claude Sonnet 5 lists at $2 and $10.

Is Claude Sonnet 5 or DeepSeek-R1 better for coding?

Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 46.3 in the Noometry coding category.

Which has the bigger context window?

Claude Sonnet 5 does, with 1M tokens against 164K.

How many benchmarks do Claude Sonnet 5 and DeepSeek-R1 share?

27 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and DeepSeek-R1 has 52.