Noometry

Model comparison

DeepSeek Coder 6.7B vs Qwen3.8 Max

Qwen3.8 Max has enough public results to be ranked (#22); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

DeepSeek Coder 6.7B DeepSeek

37.6

Unranked Sparse

Qwen3.8 Max Alibaba (Qwen)

56.8

Rank #22 Confirmed

Summary

  • They share 1 benchmark with published results for both. DeepSeek Coder 6.7B 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 53.5 to 35.8.
  • DeepSeek Coder 6.7B has downloadable open weights; the other is API-only.

Side by side

DeepSeek Coder 6.7BQwen3.8 Max
ProviderDeepSeekAlibaba (Qwen)
Noometry Index37.656.8
Released2023-11-022026-08-02
WeightsOpenProprietary
Context window—1M
Max output—131K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked939

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

Category by category

Coding Qwen3.8 Max leads

DeepSeek Coder 6.7B: 35.8 (#219), Qwen3.8 Max: 53.5 (#29)

BenchmarkDeepSeek Coder 6.7BQwen3.8 Max
DeepSWE—57.5%
LMArena WebDev—1674
FrontierSWE—17.8%
SciCode—53.2%
BigCodeBench Instruct35.5%—
LMArena Coding—1502
BigCodeBench Complete43.8%—
HumanEval+71.3%—
MBPP+65.6%—

Agentic & Tool Use Not comparable

DeepSeek Coder 6.7B: —, Qwen3.8 Max: 45.4 (#14)

BenchmarkDeepSeek Coder 6.7BQwen3.8 Max
APEX-Agents—63.3%
τ²-bench Banking—55.1%
GDP.pdf—23.2%

Reasoning Not comparable

DeepSeek Coder 6.7B: —, Qwen3.8 Max: 54.4 (#26)

BenchmarkDeepSeek Coder 6.7BQwen3.8 Max
Epoch Capabilities Index89.62156.41
NYT Connections (extended)—88.3%
CritPt—20%
Chess Puzzles—40%
LMArena Hard Prompts—1496
Mystery Game Puzzles—38%
DTBench—92%
LMCA—46.2%
WinoGrande57.6%—

Math Not comparable

DeepSeek Coder 6.7B: —, Qwen3.8 Max: 73.2 (#20)

BenchmarkDeepSeek Coder 6.7BQwen3.8 Max
FrontierMath (Tiers 1-3)—74.7%
FrontierMath Tier 4—46.3%
OTIS Mock AIME 2024-2025—100%
ProofBench—58%
LMArena Math—1499
GSM8K21.3%—

Knowledge Not comparable

DeepSeek Coder 6.7B: —, Qwen3.8 Max: 61.7 (#27)

BenchmarkDeepSeek Coder 6.7BQwen3.8 Max
GPQA Diamond—92.7%
SimpleQA Verified—47.3%
LMArena Expert—1507
ARC (AI2) Challenge36.4%—
MMLU36.4%—

Multimodal Not comparable

DeepSeek Coder 6.7B: —, Qwen3.8 Max: 37.2 (#75)

BenchmarkDeepSeek Coder 6.7BQwen3.8 Max
LMArena Vision—1314
Furniture Assembly—20%

Multilingual Not comparable

DeepSeek Coder 6.7B: —, Qwen3.8 Max: 56.7 (#18)

BenchmarkDeepSeek Coder 6.7BQwen3.8 Max
LMArena Non-English—1472
LMArena Chinese—1538
LMArena French—1503
LMArena German—1483
LMArena Japanese—1467
LMArena Korean—1461
LMArena Russian—1481
LMArena Spanish—1492

Instruction Following Not comparable

DeepSeek Coder 6.7B: —, Qwen3.8 Max: 77.6 (#17)

BenchmarkDeepSeek Coder 6.7BQwen3.8 Max
LMArena Instruction Following—1479

Long Context Not comparable

DeepSeek Coder 6.7B: —, Qwen3.8 Max: 45.6 (#31)

BenchmarkDeepSeek Coder 6.7BQwen3.8 Max
LMArena Longer Query—1489

Writing & Preference Not comparable

DeepSeek Coder 6.7B: —, Qwen3.8 Max: 67.1 (#30)

BenchmarkDeepSeek Coder 6.7BQwen3.8 Max
LMArena Text—1483
LMArena Creative Writing—1479
LMArena Multi-Turn—1489

Frequently asked questions

Is DeepSeek Coder 6.7B better than Qwen3.8 Max?

Qwen3.8 Max has enough public results to be ranked (#22); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.

Is DeepSeek Coder 6.7B or Qwen3.8 Max better for coding?

Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 35.8 in the Noometry coding category.

How many benchmarks do DeepSeek Coder 6.7B and Qwen3.8 Max share?

1 benchmark has published results for both models. DeepSeek Coder 6.7B has 9 scored results on Noometry and Qwen3.8 Max has 39.

Related comparisons

Go deeper