Noometry

Model comparison

Claude Opus 4.5 vs DeepSeek-V3

Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 39.5 on the Noometry Index. DeepSeek-V3 costs 25× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.

Last verified . 30 shared benchmarks.

Claude Opus 4.5 Anthropic

50.5

Rank #47 Confirmed

DeepSeek-V3 DeepSeek

39.5

Rank #166 Confirmed

Summary

  • They share 30 benchmarks with published results for both. Claude Opus 4.5 scores higher in 8 categories and DeepSeek-V3 in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Opus 4.5 leads 42.6 to 20.5.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 86.1% for Claude Opus 4.5 and 37.8% for DeepSeek-V3.
  • DeepSeek-V3 is cheaper at $0.24 / $0.90 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 has downloadable open weights; the other is API-only.

Side by side

Claude Opus 4.5DeepSeek-V3
ProviderAnthropicDeepSeek
Noometry Index50.539.5
Released2025-11-012024-12-26
WeightsProprietaryOpen
Context window200K164K
Max output64K164K
Input $ / M tokens$5$0.24
Output $ / M tokens$25$0.90
Results tracked6960

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: 42.3 (#106)

BenchmarkClaude Opus 4.5DeepSeek-V3
WeirdML63.7%36.1%
LMArena Coding15041368
SWE-bench Verified76.7%—
SWE-bench Verified (bash only)76.8%—
Aider Polyglot—55.1%
LMArena WebDev1494—
SWE-bench Multilingual70.7%—
SciCode—35.8%
GSO26.5%—
BigCodeBench Instruct—50%
LiveBench Coding—70.9%
BigCodeBench Complete—62.2%
ALE-Bench1,025—
AlgoTune1.77—
HumanEval+—86.6%
MBPP+—73%

Agentic & Tool Use Not comparable

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

BenchmarkClaude Opus 4.5DeepSeek-V3
METR Time Horizons75%49.6%
Terminal-Bench63.1%—
Berkeley Function Calling Leaderboard77.5%—
GDPval45.5%—
Remote Labor Index3.8%—
τ²-bench Airline84%—
τ²-bench Banking24.7%—
τ²-bench Retail79.6%—
τ²-bench Telecom92.3%—
Cybench82%—
DeepResearch Bench54.8%—
OSWorld66.3%—
BALROG43.5%—
LMArena Search1180—
Vending-Bench 24,967—

Reasoning Claude Opus 4.5 leads

Claude Opus 4.5: 42.6 (#51), DeepSeek-V3: 20.5 (#236)

BenchmarkClaude Opus 4.5DeepSeek-V3
SimpleBench62%27.2%
Kagi LLM Benchmark80.2%52.3%
LMArena Hard Prompts14761365
DTBench89.9%64.8%
LMCA44.5%15.5%
Epoch Capabilities Index150.09135.94
ForecastBench60.759.1
ARC-AGI-237.6%—
NYT Connections (extended)52.5%—
ARC-AGI-180%—
CritPt—0%
Chess Puzzles12%—
EnigmaEval11.9%—
EBR-Bench14.3%—
LiveBench Reasoning—65.8%
Mystery Game Puzzles22%—
LiveBench Data Analysis—60.9%
BIG-Bench Hard—87.5%
HellaSwag—88.9%
LiveBench—66.9%
PIQA—84.7%
WinoGrande—85.2%

Math Claude Opus 4.5 leads

Claude Opus 4.5: 38.6 (#132), DeepSeek-V3: 32.1 (#219)

BenchmarkClaude Opus 4.5DeepSeek-V3
OTIS Mock AIME 2024-202586.1%37.8%
LMArena Math14631373
FrontierMath (Feb 2025 set)20.7%1.7%
FrontierMath (Tiers 1-3)34.4%—
FrontierMath Tier 44.9%—
ProofBench36%—
Omni-MATH—40.3%
LiveBench Math—73.5%
MATH Level 5—75.5%
FrontierMath Tier 4 (v1)4.2%—

Knowledge Claude Opus 4.5 leads

Claude Opus 4.5: 56.5 (#44), DeepSeek-V3: 37.5 (#155)

BenchmarkClaude Opus 4.5DeepSeek-V3
GPQA Diamond86%67.6%
Vectara Hallucination Rate10.9%6.1%
LMArena Expert14871351
Humanity's Last Exam25.2%—
SimpleQA Verified45.7%—
MMLU-Pro—72.3%
Confabulations—26.1%
GPQA (HELM)—53.8%
ARC (AI2) Challenge—95.3%
MMLU—87.2%
TriviaQA—82.9%

Multimodal Not comparable

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

BenchmarkClaude Opus 4.5DeepSeek-V3
GeoBench75%—
VPCT40%—
Furniture Assembly28.3%—
LMArena Document1462—

Multilingual Claude Opus 4.5 leads

Claude Opus 4.5: 54.3 (#47), DeepSeek-V3: 48.5 (#143)

BenchmarkClaude Opus 4.5DeepSeek-V3
LMArena Non-English14381358
LMArena Chinese14701391
LMArena French14711385
LMArena German14491374
LMArena Japanese14161333
LMArena Korean14241319
LMArena Russian14471373
LMArena Spanish14581358

Instruction Following Claude Opus 4.5 leads

Claude Opus 4.5: 77.5 (#19), DeepSeek-V3: 72.8 (#130)

BenchmarkClaude Opus 4.5DeepSeek-V3
LMArena Instruction Following14781345
LiveBench Instruction Following—81.5%
IFEval—83.2%

Long Context Claude Opus 4.5 leads

Claude Opus 4.5: 46.5 (#22), DeepSeek-V3: 34.0 (#253)

BenchmarkClaude Opus 4.5DeepSeek-V3
LMArena Longer Query14801352
Fiction.LiveBench—50%
CL-bench21.1%—

Writing & Preference Claude Opus 4.5 leads

Claude Opus 4.5: 68.1 (#28), DeepSeek-V3: 57.4 (#130)

BenchmarkClaude Opus 4.5DeepSeek-V3
LMArena Text14511375
LMArena Creative Writing14451364
EQ-Bench Creative Writing16871472
LMArena Multi-Turn14661389
Short-Story Creative Writing—77%
WildBench—83%
LiveBench Language—49.1%

Frequently asked questions

Is Claude Opus 4.5 better than DeepSeek-V3?

Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 39.5 on the Noometry Index. DeepSeek-V3 costs 25× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.

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

DeepSeek-V3 is cheaper. It lists at $0.24 per million input tokens and $0.90 per million output tokens; Claude Opus 4.5 lists at $5 and $25.

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

Claude Opus 4.5 scores higher on coding benchmarks: 54.8 versus 42.3 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 share?

30 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and DeepSeek-V3 has 60.

Related comparisons

Go deeper