Noometry

Model comparison

Deepseek Coder v2 vs Qwen3 Max

Qwen3 Max is the stronger model overall, scoring 43.7 to 35.9 on the Noometry Index.

Last verified . 17 shared benchmarks.

Deepseek Coder v2 DeepSeek

35.9

Rank #220 Confirmed

Qwen3 Max Alibaba (Qwen)

43.7

Rank #87 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Deepseek Coder v2 scores higher in 1 category and Qwen3 Max in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Qwen3 Max leads 62.4 to 38.2.
  • Deepseek Coder v2 has downloadable open weights; the other is API-only.

Side by side

Deepseek Coder v2Qwen3 Max
ProviderDeepSeekAlibaba (Qwen)
Noometry Index35.943.7
Released2024-06-172025-09-23
WeightsOpenProprietary
Context window—262K
Max output—66K
Input $ / M tokens—$1.20
Output $ / M tokens—$6
Results tracked2433

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

Category by category

Coding Qwen3 Max leads

Deepseek Coder v2: 38.1 (#183), Qwen3 Max: 43.0 (#93)

BenchmarkDeepseek Coder v2Qwen3 Max
LMArena Coding12511456
BigCodeBench Instruct48.2%—
BigCodeBench Complete59.7%—
ALE-Bench—370.45
HumanEval+82.3%—
MBPP+75.1%—

Agentic & Tool Use Not comparable

Deepseek Coder v2: —, Qwen3 Max: —

BenchmarkDeepseek Coder v2Qwen3 Max
Vending-Bench 2—71.56

Reasoning Too close to call

Deepseek Coder v2: 23.6 (#176), Qwen3 Max: 22.6 (#190)

BenchmarkDeepseek Coder v2Qwen3 Max
LMArena Hard Prompts12071448
Kagi LLM Benchmark—72.5%
NYT Connections (extended)—30.1%
Chess Puzzles—4%
Mystery Game Puzzles—5%
DTBench—82.1%
LMCA—28.3%
Epoch Capabilities Index—142.38
WinoGrande83.7%—

Math Qwen3 Max leads

Deepseek Coder v2: 34.9 (#190), Qwen3 Max: 38.7 (#131)

BenchmarkDeepseek Coder v2Qwen3 Max
LMArena Math12411446
FrontierMath (Tiers 1-3)—18.9%
OTIS Mock AIME 2024-2025—73.3%
MATH Level 5—97.1%
GSM8K94.5%—

Knowledge Qwen3 Max leads

Deepseek Coder v2: 32.3 (#212), Qwen3 Max: 48.1 (#78)

BenchmarkDeepseek Coder v2Qwen3 Max
LMArena Expert11811455
GPQA Diamond—72.6%
SimpleQA Verified—48.7%
ARC (AI2) Challenge64.3%—

Multilingual Qwen3 Max leads

Deepseek Coder v2: 36.3 (#240), Qwen3 Max: 53.7 (#62)

BenchmarkDeepseek Coder v2Qwen3 Max
LMArena Non-English11821429
LMArena Chinese12011478
LMArena French11851449
LMArena German11641463
LMArena Japanese11261397
LMArena Korean11041399
LMArena Russian11881428
LMArena Spanish11531462

Instruction Following Qwen3 Max leads

Deepseek Coder v2: 61.7 (#242), Qwen3 Max: 74.8 (#87)

BenchmarkDeepseek Coder v2Qwen3 Max
LMArena Instruction Following11801419

Long Context Qwen3 Max leads

Deepseek Coder v2: 37.0 (#224), Qwen3 Max: 41.6 (#134)

BenchmarkDeepseek Coder v2Qwen3 Max
LMArena Longer Query12191438
Fiction.LiveBench—66.7%
CL-bench—14.5%

Writing & Preference Qwen3 Max leads

Deepseek Coder v2: 38.2 (#253), Qwen3 Max: 62.4 (#76)

BenchmarkDeepseek Coder v2Qwen3 Max
LMArena Text11911439
LMArena Creative Writing11201402
LMArena Multi-Turn11771446

Frequently asked questions

Is Deepseek Coder v2 better than Qwen3 Max?

Qwen3 Max is the stronger model overall, scoring 43.7 to 35.9 on the Noometry Index.

Is Deepseek Coder v2 or Qwen3 Max better for coding?

Qwen3 Max scores higher on coding benchmarks: 43.0 versus 38.1 in the Noometry coding category.

How many benchmarks do Deepseek Coder v2 and Qwen3 Max share?

17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Qwen3 Max has 33.

Related comparisons

Go deeper