Noometry

Model comparison

Claude 2.1 vs DeepSeek-V3

DeepSeek-V3 is the stronger model overall, scoring 39.5 to 25.2 on the Noometry Index.

Last verified . 7 shared benchmarks.

Claude 2.1 Anthropic

25.2

Rank #345 Reported

DeepSeek-V3 DeepSeek

39.5

Rank #166 Confirmed

Summary

  • They share 7 benchmarks with published results for both. Claude 2.1 scores higher in 1 category and DeepSeek-V3 in 3 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where DeepSeek-V3 leads 37.5 to 15.4.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.9% for Claude 2.1 and 37.8% for DeepSeek-V3.
  • DeepSeek-V3 has downloadable open weights; the other is API-only.

Side by side

Claude 2.1DeepSeek-V3
ProviderAnthropicDeepSeek
Noometry Index25.239.5
Released2023-11-212024-12-26
WeightsProprietaryOpen
Context window—164K
Max output—164K
Input $ / M tokens—$0.24
Output $ / M tokens—$0.90
Results tracked760

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

Category by category

Coding DeepSeek-V3 leads

Claude 2.1: 26.2 (#327), DeepSeek-V3: 42.3 (#106)

BenchmarkClaude 2.1DeepSeek-V3
WeirdML7.1%36.1%
Aider Polyglot—55.1%
SciCode—35.8%
BigCodeBench Instruct—50%
LiveBench Coding—70.9%
LMArena Coding—1368
BigCodeBench Complete—62.2%
HumanEval+—86.6%
MBPP+—73%

Agentic & Tool Use Not comparable

Claude 2.1: —, DeepSeek-V3: —

BenchmarkClaude 2.1DeepSeek-V3
METR Time Horizons—49.6%

Reasoning Too close to call

Claude 2.1: 21.4 (#221), DeepSeek-V3: 20.5 (#236)

BenchmarkClaude 2.1DeepSeek-V3
DTBench51%64.8%
Epoch Capabilities Index119.27135.94
ForecastBench54.259.1
SimpleBench—27.2%
Kagi LLM Benchmark—52.3%
CritPt—0%
LiveBench Reasoning—65.8%
LMArena Hard Prompts—1365
LiveBench Data Analysis—60.9%
LMCA—15.5%
BIG-Bench Hard—87.5%
HellaSwag—88.9%
LiveBench—66.9%
PIQA—84.7%
WinoGrande—85.2%

Math DeepSeek-V3 leads

Claude 2.1: 10.2 (#315), DeepSeek-V3: 32.1 (#219)

BenchmarkClaude 2.1DeepSeek-V3
OTIS Mock AIME 2024-20251.9%37.8%
Omni-MATH—40.3%
LiveBench Math—73.5%
LMArena Math—1373
MATH Level 5—75.5%
FrontierMath (Feb 2025 set)—1.7%

Knowledge DeepSeek-V3 leads

Claude 2.1: 15.4 (#292), DeepSeek-V3: 37.5 (#155)

BenchmarkClaude 2.1DeepSeek-V3
GPQA Diamond33%67.6%
MMLU73.5%87.2%
MMLU-Pro—72.3%
Confabulations—26.1%
Vectara Hallucination Rate—6.1%
GPQA (HELM)—53.8%
LMArena Expert—1351
ARC (AI2) Challenge—95.3%
TriviaQA—82.9%

Multilingual Not comparable

Claude 2.1: —, DeepSeek-V3: 48.5 (#143)

BenchmarkClaude 2.1DeepSeek-V3
LMArena Non-English—1358
LMArena Chinese—1391
LMArena French—1385
LMArena German—1374
LMArena Japanese—1333
LMArena Korean—1319
LMArena Russian—1373
LMArena Spanish—1358

Instruction Following Not comparable

Claude 2.1: —, DeepSeek-V3: 72.8 (#130)

BenchmarkClaude 2.1DeepSeek-V3
LiveBench Instruction Following—81.5%
IFEval—83.2%
LMArena Instruction Following—1345

Long Context Not comparable

Claude 2.1: —, DeepSeek-V3: 34.0 (#253)

BenchmarkClaude 2.1DeepSeek-V3
Fiction.LiveBench—50%
LMArena Longer Query—1352

Writing & Preference Not comparable

Claude 2.1: —, DeepSeek-V3: 57.4 (#130)

BenchmarkClaude 2.1DeepSeek-V3
LMArena Text—1375
LMArena Creative Writing—1364
Short-Story Creative Writing—77%
EQ-Bench Creative Writing—1472
WildBench—83%
LMArena Multi-Turn—1389
LiveBench Language—49.1%

Frequently asked questions

Is Claude 2.1 better than DeepSeek-V3?

DeepSeek-V3 is the stronger model overall, scoring 39.5 to 25.2 on the Noometry Index.

Is Claude 2.1 or DeepSeek-V3 better for coding?

DeepSeek-V3 scores higher on coding benchmarks: 42.3 versus 26.2 in the Noometry coding category.

How many benchmarks do Claude 2.1 and DeepSeek-V3 share?

7 benchmarks have published results for both models. Claude 2.1 has 7 scored results on Noometry and DeepSeek-V3 has 60.

Related comparisons

Go deeper