Model comparison

Claude Sonnet 4.6 vs DeepSeek-R1

Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 42.3 on the Noometry Index. DeepSeek-R1 costs 6.6× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.

Last verified October 10, 2026. 30 shared benchmarks.

Claude Sonnet 4.6 Anthropic

50.3

Rank #50 Confirmed

DeepSeek-R1

DeepSeek

42.3

Rank #115 Confirmed

Summary

They share 30 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 8 categories and DeepSeek-R1 in 1 category; 7 gaps are clear of the uncertainty.
The widest gap is in reasoning, where Claude Sonnet 4.6 leads 46.1 to 18.6.
The biggest single-benchmark swing is ARC-AGI-1: 86.5% for Claude Sonnet 4.6 and 21.2% for DeepSeek-R1.
DeepSeek-R1 is cheaper at $0.50 / $2.15 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.6.
Claude Sonnet 4.6 accepts more context: 1M tokens versus 164K.

Side by side

Claude Sonnet 4.6 and DeepSeek-R1 specifications
	Claude Sonnet 4.6	DeepSeek-R1
Provider	Anthropic	DeepSeek
Noometry Index	50.3	42.3
Released	2026-02-17	2025-01-20
Weights	Proprietary	Proprietary
Context window	1M	164K
Max output	128K	64K
Input $ / M tokens	$3	$0.50
Output $ / M tokens	$15	$2.15
Results tracked	57	52

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

Category by category

Coding Too close to call

Claude Sonnet 4.6: 46.3 (#67), DeepSeek-R1: 46.3 (#68)

Coding benchmarks
Benchmark	Claude Sonnet 4.6	DeepSeek-R1
SciCode	46.8%	35.7%
WeirdML	66.1%	41.6%
LMArena Coding	1504	1427
ALE-Bench	1,327	804.12
SWE-bench Verified	75.2%	—
DeepSWE	29.9%	—
FrontierCode	24.3%	—
Aider Polyglot	—	71.4%
LMArena WebDev	1522	—
LiveBench Coding	—	66.7%
AlgoTune	—	1.7

Agentic & Tool Use Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 39.1 (#28), DeepSeek-R1: 30.7 (#75)

Agentic & Tool Use benchmarks
Benchmark	Claude Sonnet 4.6	DeepSeek-R1
DeepResearch Bench	54.9%	35.1%
Terminal-Bench	53.4%	—
APEX-Agents	43%	—
OSWorld 2.0	9.3%	—
OSWorld	72.1%	—
BALROG	—	34.9%
ExploitBench	23.6%	—
GBAEval	48.8%	—
GDP.pdf	18%	—
LMArena Search	1221	—
METR Time Horizons	—	53.8%
Vending-Bench 2	7,204	—

Reasoning Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 46.1 (#45), DeepSeek-R1: 18.6 (#278)

Reasoning benchmarks
Benchmark	Claude Sonnet 4.6	DeepSeek-R1
ARC-AGI-2	60.4%	1.3%
ARC-AGI-1	86.5%	21.2%
CritPt	3.1%	1.1%
LMArena Hard Prompts	1484	1416
Epoch Capabilities Index	152.24	141.29
ForecastBench	62	60
SimpleBench	—	40.8%
Kagi LLM Benchmark	—	69.4%
NYT Connections (extended)	80.9%	—
Chess Puzzles	13%	—
Thematic Generalization	76.3%	—
LiveBench Reasoning	—	83.2%
Mystery Game Puzzles	16%	—
DTBench	89.9%	—
LiveBench Data Analysis	—	69.8%
LMCA	46.5%	—
LiveBench	—	71.6%

Math Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 52.9 (#49), DeepSeek-R1: 43.8 (#79)

Math benchmarks
Benchmark	Claude Sonnet 4.6	DeepSeek-R1
OTIS Mock AIME 2024-2025	85.8%	66.4%
LMArena Math	1462	1400
ProofBench	45%	—
Omni-MATH	—	42.4%
LiveBench Math	—	80.7%
MATH Level 5	—	96.6%
FrontierMath (Feb 2025 set)	32.4%	—
FrontierMath Tier 4 (v1)	8.3%	—

Knowledge Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 51.7 (#65), DeepSeek-R1: 44.5 (#87)

Knowledge benchmarks
Benchmark	Claude Sonnet 4.6	DeepSeek-R1
GPQA Diamond	87.4%	76.3%
Vectara Hallucination Rate	10.6%	11.3%
LMArena Expert	1500	1394
SimpleQA Verified	35.5%	—
MMLU-Pro	—	79.3%
Confabulations	—	12.7%
GPQA (HELM)	—	66.6%

Multimodal Not comparable

Claude Sonnet 4.6: 38.0 (#68), DeepSeek-R1: —

Multimodal benchmarks
Benchmark	Claude Sonnet 4.6	DeepSeek-R1
LMArena Vision	1283	—
Blueprint-Bench 2	6.7%	—
LMArena Document	1482	—

Multilingual Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 54.4 (#41), DeepSeek-R1: 52.4 (#85)

Multilingual benchmarks
Benchmark	Claude Sonnet 4.6	DeepSeek-R1
LMArena Non-English	1440	1412
LMArena Chinese	1491	1442
LMArena French	1465	1417
LMArena German	1428	1404
LMArena Japanese	1420	1391
LMArena Korean	1411	1360
LMArena Russian	1440	1423
LMArena Spanish	1464	1411

Instruction Following Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 77.4 (#25), DeepSeek-R1: 72.0 (#143)

Instruction Following benchmarks
Benchmark	Claude Sonnet 4.6	DeepSeek-R1
LMArena Instruction Following	1475	1382
LiveBench Instruction Following	—	80.5%
IFEval	—	78.4%

Long Context Too close to call

Claude Sonnet 4.6: 45.3 (#44), DeepSeek-R1: 45.4 (#36)

Long Context benchmarks
Benchmark	Claude Sonnet 4.6	DeepSeek-R1
LMArena Longer Query	1479	1391
Fiction.LiveBench	—	75%

Writing & Preference Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 70.2 (#22), DeepSeek-R1: 61.4 (#88)

Writing & Preference benchmarks
Benchmark	Claude Sonnet 4.6	DeepSeek-R1
LMArena Text	1458	1428
LMArena Creative Writing	1435	1405
EQ-Bench Creative Writing	1810	1500
LMArena Multi-Turn	1464	1405
Short-Story Creative Writing	—	83%
WildBench	—	82.8%
EQ-Bench 4	1207	—
LiveBench Language	—	48.5%

Frequently asked questions

Is Claude Sonnet 4.6 better than DeepSeek-R1?

Which is cheaper, Claude Sonnet 4.6 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 4.6 lists at $3 and $15.

Is Claude Sonnet 4.6 or DeepSeek-R1 better for coding?

They score almost the same on coding (46.3 vs 46.3); test both on your own repository before choosing.

Which has the bigger context window?

Claude Sonnet 4.6 does, with 1M tokens against 164K.

How many benchmarks do Claude Sonnet 4.6 and DeepSeek-R1 share?

30 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and DeepSeek-R1 has 52.