Noometry

Model comparison

DeepSeek Coder 33B vs Qwen3.8 Max

Qwen3.8 Max has enough public results to be ranked (#21); DeepSeek Coder 33B does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

DeepSeek Coder 33B DeepSeek

38.3

Unranked Sparse

Qwen3.8 Max Alibaba (Qwen)

56.0

Rank #21 Confirmed

Summary

  • They share 1 benchmark with published results for both. DeepSeek Coder 33B scores higher in 0 categories and Qwen3.8 Max in 1 category; one gap is clear of the uncertainty.
  • The widest gap is in coding, where Qwen3.8 Max leads 52.3 to 37.4.
  • DeepSeek Coder 33B has downloadable open weights; the other is API-only.

Side by side

DeepSeek Coder 33BQwen3.8 Max
ProviderDeepSeekAlibaba (Qwen)
Noometry Index38.356.0
Released2023-11-022026-08-02
WeightsOpenProprietary
Context window—1M
Max output—131K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked938

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

Category by category

Coding Qwen3.8 Max leads

DeepSeek Coder 33B: 37.4 (#180), Qwen3.8 Max: 52.3 (#30)

BenchmarkDeepSeek Coder 33BQwen3.8 Max
DeepSWE—57.5%
LMArena WebDev—1671
FrontierSWE—15.8%
SciCode—52.9%
BigCodeBench Instruct42%—
LMArena Coding—1499
BigCodeBench Complete51.1%—
HumanEval+75%—
MBPP+70.1%—

Agentic & Tool Use Not comparable

DeepSeek Coder 33B: —, Qwen3.8 Max: 42.6 (#17)

BenchmarkDeepSeek Coder 33BQwen3.8 Max
τ²-bench Banking—55.1%
GDP.pdf—23.2%

Reasoning Not comparable

DeepSeek Coder 33B: —, Qwen3.8 Max: 53.4 (#26)

BenchmarkDeepSeek Coder 33BQwen3.8 Max
Epoch Capabilities Index95.74156.69
NYT Connections (extended)—88.3%
CritPt—20%
Chess Puzzles—40%
LMArena Hard Prompts—1493
Mystery Game Puzzles—38%
DTBench—92%
LMCA—46.2%
WinoGrande62%—

Math Not comparable

DeepSeek Coder 33B: —, Qwen3.8 Max: 73.1 (#15)

BenchmarkDeepSeek Coder 33BQwen3.8 Max
FrontierMath (Tiers 1-3)—74.7%
FrontierMath Tier 4—46.3%
OTIS Mock AIME 2024-2025—100%
ProofBench—58%
LMArena Math—1498
GSM8K35.4%—

Knowledge Not comparable

DeepSeek Coder 33B: —, Qwen3.8 Max: 61.7 (#25)

BenchmarkDeepSeek Coder 33BQwen3.8 Max
GPQA Diamond—92.7%
SimpleQA Verified—47.3%
LMArena Expert—1504
ARC (AI2) Challenge42.2%—
MMLU39.4%—

Multimodal Not comparable

DeepSeek Coder 33B: —, Qwen3.8 Max: 36.9 (#70)

BenchmarkDeepSeek Coder 33BQwen3.8 Max
LMArena Vision—1314
Furniture Assembly—20%

Multilingual Not comparable

DeepSeek Coder 33B: —, Qwen3.8 Max: 56.6 (#18)

BenchmarkDeepSeek Coder 33BQwen3.8 Max
LMArena Non-English—1468
LMArena Chinese—1537
LMArena French—1502
LMArena German—1489
LMArena Japanese—1466
LMArena Korean—1467
LMArena Russian—1478
LMArena Spanish—1495

Instruction Following Not comparable

DeepSeek Coder 33B: —, Qwen3.8 Max: 77.7 (#19)

BenchmarkDeepSeek Coder 33BQwen3.8 Max
LMArena Instruction Following—1478

Long Context Not comparable

DeepSeek Coder 33B: —, Qwen3.8 Max: 45.5 (#30)

BenchmarkDeepSeek Coder 33BQwen3.8 Max
LMArena Longer Query—1486

Writing & Preference Not comparable

DeepSeek Coder 33B: —, Qwen3.8 Max: 67.0 (#31)

BenchmarkDeepSeek Coder 33BQwen3.8 Max
LMArena Text—1480
LMArena Creative Writing—1478
LMArena Multi-Turn—1487

Frequently asked questions

Is DeepSeek Coder 33B better than Qwen3.8 Max?

Qwen3.8 Max has enough public results to be ranked (#21); DeepSeek Coder 33B does not yet, so treat this comparison as directional.

Is DeepSeek Coder 33B or Qwen3.8 Max better for coding?

Qwen3.8 Max scores higher on coding benchmarks: 52.3 versus 37.4 in the Noometry coding category.

How many benchmarks do DeepSeek Coder 33B and Qwen3.8 Max share?

1 benchmark has published results for both models. DeepSeek Coder 33B has 9 scored results on Noometry and Qwen3.8 Max has 38.

Related comparisons

Go deeper