Model comparison

Claude Opus 4.5 vs DeepSeek-V3.1

Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 42.8 on the Noometry Index. DeepSeek-V3.1 costs 24× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.

Last verified October 11, 2026. 26 shared benchmarks.

Claude Opus 4.5 Anthropic

50.5

Rank #47 Confirmed

DeepSeek-V3.1

DeepSeek

42.8

Rank #108 Confirmed

Summary

They share 26 benchmarks with published results for both. Claude Opus 4.5 scores higher in 7 categories and DeepSeek-V3.1 in 1 category; 7 gaps are clear of the uncertainty.
The widest gap is in reasoning, where Claude Opus 4.5 leads 42.6 to 27.9.
The biggest single-benchmark swing is Kagi LLM Benchmark: 80.2% for Claude Opus 4.5 and 53.2% for DeepSeek-V3.1.
DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $5 / $25 for Claude Opus 4.5.
Claude Opus 4.5 accepts more context: 200K tokens versus 164K.
DeepSeek-V3.1 has downloadable open weights; the other is API-only.

Side by side

Claude Opus 4.5 and DeepSeek-V3.1 specifications
	Claude Opus 4.5	DeepSeek-V3.1
Provider	Anthropic	DeepSeek
Noometry Index	50.5	42.8
Released	2025-11-01	2025-08-21
Weights	Proprietary	Open
Context window	200K	164K
Max output	64K	8K
Input $ / M tokens	$5	$0.25
Output $ / M tokens	$25	$0.95
Results tracked	69	27

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

Category by category

Coding Claude Opus 4.5 leads

Claude Opus 4.5: 54.8 (#27), DeepSeek-V3.1: 40.3 (#144)

Coding benchmarks
Benchmark	Claude Opus 4.5	DeepSeek-V3.1
WeirdML	63.7%	38.4%
LMArena Coding	1504	1417
SWE-bench Verified	76.7%	—
SWE-bench Verified (bash only)	76.8%	—
LMArena WebDev	1494	—
SWE-bench Multilingual	70.7%	—
GSO	26.5%	—
ALE-Bench	1,025	—
AlgoTune	1.77	—

Agentic & Tool Use Not comparable

Claude Opus 4.5: 47.3 (#12), DeepSeek-V3.1: —

Agentic & Tool Use benchmarks
Benchmark	Claude Opus 4.5	DeepSeek-V3.1
Terminal-Bench	63.1%	—
Berkeley Function Calling Leaderboard	77.5%	—
GDPval	45.5%	—
Remote Labor Index	3.8%	—
τ²-bench Airline	84%	—
τ²-bench Banking	24.7%	—
τ²-bench Retail	79.6%	—
τ²-bench Telecom	92.3%	—
Cybench	82%	—
DeepResearch Bench	54.8%	—
OSWorld	66.3%	—
BALROG	43.5%	—
LMArena Search	1180	—
METR Time Horizons	75%	—
Vending-Bench 2	4,967	—

Reasoning Claude Opus 4.5 leads

Claude Opus 4.5: 42.6 (#51), DeepSeek-V3.1: 27.9 (#110)

Reasoning benchmarks
Benchmark	Claude Opus 4.5	DeepSeek-V3.1
SimpleBench	62%	40%
Kagi LLM Benchmark	80.2%	53.2%
LMArena Hard Prompts	1476	1417
DTBench	89.9%	82.7%
LMCA	44.5%	24.3%
Epoch Capabilities Index	150.09	139.92
ForecastBench	60.7	58
ARC-AGI-2	37.6%	—
NYT Connections (extended)	52.5%	—
ARC-AGI-1	80%	—
Chess Puzzles	12%	—
EnigmaEval	11.9%	—
EBR-Bench	14.3%	—
Mystery Game Puzzles	22%	—

Math Too close to call

Claude Opus 4.5: 38.6 (#132), DeepSeek-V3.1: 38.9 (#122)

Math benchmarks
Benchmark	Claude Opus 4.5	DeepSeek-V3.1
LMArena Math	1463	1420
FrontierMath (Tiers 1-3)	34.4%	—
FrontierMath Tier 4	4.9%	—
OTIS Mock AIME 2024-2025	86.1%	—
ProofBench	36%	—
FrontierMath (Feb 2025 set)	20.7%	—
FrontierMath Tier 4 (v1)	4.2%	—

Knowledge Claude Opus 4.5 leads

Claude Opus 4.5: 56.5 (#44), DeepSeek-V3.1: 43.7 (#90)

Knowledge benchmarks
Benchmark	Claude Opus 4.5	DeepSeek-V3.1
Vectara Hallucination Rate	10.9%	5.5%
LMArena Expert	1487	1405
GPQA Diamond	86%	—
Humanity's Last Exam	25.2%	—
SimpleQA Verified	45.7%	—

Multimodal Not comparable

Claude Opus 4.5: 31.4 (#107), DeepSeek-V3.1: —

Multimodal benchmarks
Benchmark	Claude Opus 4.5	DeepSeek-V3.1
GeoBench	75%	—
VPCT	40%	—
Furniture Assembly	28.3%	—
LMArena Document	1462	—

Multilingual Claude Opus 4.5 leads

Claude Opus 4.5: 54.3 (#47), DeepSeek-V3.1: 51.6 (#106)

Multilingual benchmarks
Benchmark	Claude Opus 4.5	DeepSeek-V3.1
LMArena Non-English	1438	1400
LMArena Chinese	1470	1469
LMArena French	1471	1447
LMArena German	1449	1411
LMArena Japanese	1416	1378
LMArena Korean	1424	1337
LMArena Russian	1447	1405
LMArena Spanish	1458	1431

Instruction Following Claude Opus 4.5 leads

Claude Opus 4.5: 77.5 (#19), DeepSeek-V3.1: 73.9 (#110)

Instruction Following benchmarks
Benchmark	Claude Opus 4.5	DeepSeek-V3.1
LMArena Instruction Following	1478	1400

Long Context Claude Opus 4.5 leads

Claude Opus 4.5: 46.5 (#22), DeepSeek-V3.1: 36.3 (#232)

Long Context benchmarks
Benchmark	Claude Opus 4.5	DeepSeek-V3.1
LMArena Longer Query	1480	1422
Fiction.LiveBench	—	52.8%
CL-bench	21.1%	—

Writing & Preference Claude Opus 4.5 leads

Claude Opus 4.5: 68.1 (#28), DeepSeek-V3.1: 60.3 (#98)

Writing & Preference benchmarks
Benchmark	Claude Opus 4.5	DeepSeek-V3.1
LMArena Text	1451	1420
LMArena Creative Writing	1445	1401
EQ-Bench Creative Writing	1687	1436
LMArena Multi-Turn	1466	1408

Frequently asked questions

Is Claude Opus 4.5 better than DeepSeek-V3.1?

Which is cheaper, Claude Opus 4.5 or DeepSeek-V3.1?

DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; Claude Opus 4.5 lists at $5 and $25.

Is Claude Opus 4.5 or DeepSeek-V3.1 better for coding?

Claude Opus 4.5 scores higher on coding benchmarks: 54.8 versus 40.3 in the Noometry coding category.

Which has the bigger context window?

Claude Opus 4.5 does, with 200K tokens against 164K.

How many benchmarks do Claude Opus 4.5 and DeepSeek-V3.1 share?

26 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and DeepSeek-V3.1 has 27.