Model comparison

Claude Opus 5 vs DeepSeek-R1

Claude Opus 5 is the stronger model overall, scoring 67.8 to 42.3 on the Noometry Index. DeepSeek-R1 costs 11× less per token, which makes it the better buy when Claude Opus 5's lead doesn't matter for your workload.

Last verified October 10, 2026. 29 shared benchmarks.

Claude Opus 5 Anthropic

67.8

Rank #4 Confirmed

DeepSeek-R1

DeepSeek

42.3

Rank #115 Confirmed

Summary

They share 29 benchmarks with published results for both. Claude Opus 5 scores higher in 9 categories and DeepSeek-R1 in 0 categories; 9 gaps are clear of the uncertainty.
The widest gap is in reasoning, where Claude Opus 5 leads 77.2 to 18.6.
The biggest single-benchmark swing is ARC-AGI-2: 90.4% for Claude Opus 5 and 1.3% for DeepSeek-R1.
DeepSeek-R1 is cheaper at $0.50 / $2.15 per million input/output tokens, against $5 / $25 for Claude Opus 5.
Claude Opus 5 accepts more context: 1M tokens versus 164K.

Side by side

Claude Opus 5 and DeepSeek-R1 specifications
	Claude Opus 5	DeepSeek-R1
Provider	Anthropic	DeepSeek
Noometry Index	67.8	42.3
Released	2026-07-24	2025-01-20
Weights	Proprietary	Proprietary
Context window	1M	164K
Max output	128K	64K
Input $ / M tokens	$5	$0.50
Output $ / M tokens	$25	$2.15
Results tracked	57	52

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

Category by category

Coding Claude Opus 5 leads

Claude Opus 5: 67.5 (#5), DeepSeek-R1: 46.3 (#68)

Coding benchmarks
Benchmark	Claude Opus 5	DeepSeek-R1
SciCode	56.4%	35.7%
WeirdML	91.8%	41.6%
LMArena Coding	1534	1427
ALE-Bench	2,165	804.12
DeepSWE	73.6%	—
FrontierCode	53.4%	—
Aider Polyglot	—	71.4%
CursorBench	46.6%	—
LMArena WebDev	1691	—
FrontierSWE	52%	—
LiveBench Coding	—	66.7%
AlgoTune	—	1.7

Agentic & Tool Use Claude Opus 5 leads

Claude Opus 5: 55.6 (#1), DeepSeek-R1: 30.7 (#75)

Agentic & Tool Use benchmarks
Benchmark	Claude Opus 5	DeepSeek-R1
BALROG	63.4%	34.9%
APEX-Agents	65.8%	—
OSWorld 2.0	31.4%	—
τ²-bench Banking	48.7%	—
DeepResearch Bench	—	35.1%
PostTrainBench	35%	—
GBAEval	79.6%	—
GDP.pdf	24%	—
METR Time Horizons	—	53.8%
Vending-Bench 2	11,182	—

Reasoning Claude Opus 5 leads

Claude Opus 5: 77.2 (#4), DeepSeek-R1: 18.6 (#278)

Reasoning benchmarks
Benchmark	Claude Opus 5	DeepSeek-R1
ARC-AGI-2	90.4%	1.3%
SimpleBench	80.6%	40.8%
ARC-AGI-1	97.5%	21.2%
CritPt	29.1%	1.1%
LMArena Hard Prompts	1526	1416
Epoch Capabilities Index	162.78	141.29
Kagi LLM Benchmark	—	69.4%
NYT Connections (extended)	94.3%	—
Chess Puzzles	42%	—
EBR-Bench	45.7%	—
LiveBench Reasoning	—	83.2%
Mystery Game Puzzles	59%	—
DTBench	97.9%	—
LiveBench Data Analysis	—	69.8%
LMCA	64.5%	—
Bench to the Future 3	0.12	—
ForecastBench	—	60
LiveBench	—	71.6%

Math Claude Opus 5 leads

Claude Opus 5: 86.2 (#8), DeepSeek-R1: 43.8 (#79)

Math benchmarks
Benchmark	Claude Opus 5	DeepSeek-R1
OTIS Mock AIME 2024-2025	98.9%	66.4%
LMArena Math	1531	1400
FrontierMath (Tiers 1-3)	85.6%	—
FrontierMath Tier 4	73.2%	—
ProofBench	99%	—
Omni-MATH	—	42.4%
LiveBench Math	—	80.7%
MATH Level 5	—	96.6%

Knowledge Claude Opus 5 leads

Claude Opus 5: 66.8 (#9), DeepSeek-R1: 44.5 (#87)

Knowledge benchmarks
Benchmark	Claude Opus 5	DeepSeek-R1
GPQA Diamond	93.9%	76.3%
LMArena Expert	1557	1394
SimpleQA Verified	59.9%	—
MMLU-Pro	—	79.3%
Confabulations	—	12.7%
Vectara Hallucination Rate	—	11.3%
GPQA (HELM)	—	66.6%

Multimodal Not comparable

Claude Opus 5: 50.8 (#8), DeepSeek-R1: —

Multimodal benchmarks
Benchmark	Claude Opus 5	DeepSeek-R1
LMArena Vision	1319	—
Blueprint-Bench 2	30.4%	—
Furniture Assembly	60.8%	—
LMArena Document	1516	—

Multilingual Claude Opus 5 leads

Claude Opus 5: 58.8 (#4), DeepSeek-R1: 52.4 (#85)

Multilingual benchmarks
Benchmark	Claude Opus 5	DeepSeek-R1
LMArena Non-English	1501	1412
LMArena Chinese	1574	1442
LMArena French	1519	1417
LMArena German	1524	1404
LMArena Japanese	1516	1391
LMArena Korean	1521	1360
LMArena Russian	1507	1423
LMArena Spanish	1519	1411

Instruction Following Claude Opus 5 leads

Claude Opus 5: 79.2 (#7), DeepSeek-R1: 72.0 (#143)

Instruction Following benchmarks
Benchmark	Claude Opus 5	DeepSeek-R1
LMArena Instruction Following	1517	1382
LiveBench Instruction Following	—	80.5%
IFEval	—	78.4%

Long Context Claude Opus 5 leads

Claude Opus 5: 46.5 (#21), DeepSeek-R1: 45.4 (#36)

Long Context benchmarks
Benchmark	Claude Opus 5	DeepSeek-R1
LMArena Longer Query	1515	1391
Fiction.LiveBench	—	75%

Writing & Preference Claude Opus 5 leads

Claude Opus 5: 79.2 (#1), DeepSeek-R1: 61.4 (#88)

Writing & Preference benchmarks
Benchmark	Claude Opus 5	DeepSeek-R1
LMArena Text	1507	1428
LMArena Creative Writing	1491	1405
EQ-Bench Creative Writing	2133	1500
LMArena Multi-Turn	1499	1405
Short-Story Creative Writing	—	83%
WildBench	—	82.8%
EQ-Bench 4	1385	—
LiveBench Language	—	48.5%

Frequently asked questions

Is Claude Opus 5 better than DeepSeek-R1?

Which is cheaper, Claude Opus 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 Opus 5 lists at $5 and $25.

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

Claude Opus 5 scores higher on coding benchmarks: 67.5 versus 46.3 in the Noometry coding category.

Which has the bigger context window?

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

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

29 benchmarks have published results for both models. Claude Opus 5 has 57 scored results on Noometry and DeepSeek-R1 has 52.