Noometry

Model comparison

DeepSeek-R1 vs Qwen2.5-Max

DeepSeek-R1 is the stronger model overall, scoring 42.3 to 40.7 on the Noometry Index.

Last verified . 27 shared benchmarks.

DeepSeek-R1 DeepSeek

42.3

Rank #115 Confirmed

Qwen2.5-Max Alibaba (Qwen)

40.7

Rank #146 Confirmed

Summary

  • They share 27 benchmarks with published results for both. DeepSeek-R1 scores higher in 7 categories and Qwen2.5-Max in 1 category; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where DeepSeek-R1 leads 44.5 to 35.3.
  • The biggest single-benchmark swing is LiveBench Reasoning: 83.2% for DeepSeek-R1 and 51.4% for Qwen2.5-Max.

Side by side

DeepSeek-R1Qwen2.5-Max
ProviderDeepSeekAlibaba (Qwen)
Noometry Index42.340.7
Released2025-01-202025-01-25
WeightsProprietaryProprietary
Context window164K—
Max output64K—
Input $ / M tokens$0.50—
Output $ / M tokens$2.15—
Results tracked5227

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

Category by category

Coding DeepSeek-R1 leads

DeepSeek-R1: 46.3 (#68), Qwen2.5-Max: 41.8 (#117)

BenchmarkDeepSeek-R1Qwen2.5-Max
LiveBench Coding66.7%64.4%
LMArena Coding14271359
Aider Polyglot71.4%—
SciCode35.7%—
WeirdML41.6%—
ALE-Bench804.12—
AlgoTune1.7—

Agentic & Tool Use Not comparable

DeepSeek-R1: 30.7 (#75), Qwen2.5-Max: —

BenchmarkDeepSeek-R1Qwen2.5-Max
DeepResearch Bench35.1%—
BALROG34.9%—
METR Time Horizons53.8%—

Reasoning Qwen2.5-Max leads

DeepSeek-R1: 18.6 (#278), Qwen2.5-Max: 25.6 (#147)

BenchmarkDeepSeek-R1Qwen2.5-Max
LiveBench Reasoning83.2%51.4%
LMArena Hard Prompts14161360
LiveBench Data Analysis69.8%67.9%
Epoch Capabilities Index141.29132.53
LiveBench71.6%62.3%
ARC-AGI-21.3%—
SimpleBench40.8%—
Kagi LLM Benchmark69.4%—
ARC-AGI-121.2%—
CritPt1.1%—
ForecastBench60—

Math DeepSeek-R1 leads

DeepSeek-R1: 43.8 (#79), Qwen2.5-Max: 36.9 (#162)

BenchmarkDeepSeek-R1Qwen2.5-Max
LiveBench Math80.7%58.4%
LMArena Math14001369
OTIS Mock AIME 2024-202566.4%—
Omni-MATH42.4%—
MATH Level 596.6%—

Knowledge DeepSeek-R1 leads

DeepSeek-R1: 44.5 (#87), Qwen2.5-Max: 35.3 (#186)

BenchmarkDeepSeek-R1Qwen2.5-Max
Confabulations12.7%21.8%
LMArena Expert13941337
GPQA Diamond76.3%—
MMLU-Pro79.3%—
Vectara Hallucination Rate11.3%—
GPQA (HELM)66.6%—

Multilingual DeepSeek-R1 leads

DeepSeek-R1: 52.4 (#85), Qwen2.5-Max: 48.1 (#146)

BenchmarkDeepSeek-R1Qwen2.5-Max
LMArena Non-English14121352
LMArena Chinese14421382
LMArena French14171396
LMArena German14041350
LMArena Japanese13911300
LMArena Korean13601304
LMArena Russian14231353
LMArena Spanish14111377

Instruction Following Too close to call

DeepSeek-R1: 72.0 (#143), Qwen2.5-Max: 71.3 (#152)

BenchmarkDeepSeek-R1Qwen2.5-Max
LiveBench Instruction Following80.5%75.3%
LMArena Instruction Following13821335
IFEval78.4%—

Long Context DeepSeek-R1 leads

DeepSeek-R1: 45.4 (#36), Qwen2.5-Max: 41.4 (#142)

BenchmarkDeepSeek-R1Qwen2.5-Max
LMArena Longer Query13911358
Fiction.LiveBench75%—

Writing & Preference DeepSeek-R1 leads

DeepSeek-R1: 61.4 (#88), Qwen2.5-Max: 55.4 (#146)

BenchmarkDeepSeek-R1Qwen2.5-Max
LMArena Text14281367
LMArena Creative Writing14051339
Short-Story Creative Writing83%72.9%
LMArena Multi-Turn14051364
LiveBench Language48.5%56.3%
EQ-Bench Creative Writing1500—
WildBench82.8%—

Frequently asked questions

Is DeepSeek-R1 better than Qwen2.5-Max?

DeepSeek-R1 is the stronger model overall, scoring 42.3 to 40.7 on the Noometry Index.

Is DeepSeek-R1 or Qwen2.5-Max better for coding?

DeepSeek-R1 scores higher on coding benchmarks: 46.3 versus 41.8 in the Noometry coding category.

How many benchmarks do DeepSeek-R1 and Qwen2.5-Max share?

27 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and Qwen2.5-Max has 27.

Related comparisons

Go deeper