Noometry

Model comparison

Deepseek Coder v2 vs Qwen3.7 Flash

Qwen3.7 Flash is the stronger model overall, scoring 39.9 to 35.9 on the Noometry Index.

Last verified . 0 shared benchmarks.

Deepseek Coder v2 DeepSeek

35.9

Rank #220 Confirmed

Qwen3.7 Flash Alibaba (Qwen)

39.9

Rank #156 Confirmed

Summary

  • The widest gap is in knowledge, where Qwen3.7 Flash leads 48.9 to 32.3.
  • Deepseek Coder v2 has downloadable open weights; the other is API-only.

Side by side

Deepseek Coder v2Qwen3.7 Flash
ProviderDeepSeekAlibaba (Qwen)
Noometry Index35.939.9
Released2024-06-172026-07-15
WeightsOpenProprietary
Context window—1M
Max output—131K
Input $ / M tokens—$0.03
Output $ / M tokens—$0.13
Results tracked247

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

Category by category

Coding Not comparable

Deepseek Coder v2: 38.1 (#183), Qwen3.7 Flash: —

BenchmarkDeepseek Coder v2Qwen3.7 Flash
BigCodeBench Instruct48.2%—
LMArena Coding1251—
BigCodeBench Complete59.7%—
HumanEval+82.3%—
MBPP+75.1%—

Reasoning Qwen3.7 Flash leads

Deepseek Coder v2: 23.6 (#176), Qwen3.7 Flash: 28.2 (#108)

BenchmarkDeepseek Coder v2Qwen3.7 Flash
NYT Connections (extended)—43.8%
Chess Puzzles—23%
LMArena Hard Prompts1207—
Mystery Game Puzzles—15%
Epoch Capabilities Index—144.64
WinoGrande83.7%—

Math Qwen3.7 Flash leads

Deepseek Coder v2: 34.9 (#190), Qwen3.7 Flash: 38.3 (#140)

BenchmarkDeepseek Coder v2Qwen3.7 Flash
FrontierMath (Tiers 1-3)—19.3%
OTIS Mock AIME 2024-2025—86.7%
LMArena Math1241—
GSM8K94.5%—

Knowledge Qwen3.7 Flash leads

Deepseek Coder v2: 32.3 (#212), Qwen3.7 Flash: 48.9 (#75)

BenchmarkDeepseek Coder v2Qwen3.7 Flash
GPQA Diamond—82.3%
LMArena Expert1181—
ARC (AI2) Challenge64.3%—

Multilingual Not comparable

Deepseek Coder v2: 36.3 (#240), Qwen3.7 Flash: —

BenchmarkDeepseek Coder v2Qwen3.7 Flash
LMArena Non-English1182—
LMArena Chinese1201—
LMArena French1185—
LMArena German1164—
LMArena Japanese1126—
LMArena Korean1104—
LMArena Russian1188—
LMArena Spanish1153—

Instruction Following Not comparable

Deepseek Coder v2: 61.7 (#242), Qwen3.7 Flash: —

BenchmarkDeepseek Coder v2Qwen3.7 Flash
LMArena Instruction Following1180—

Long Context Not comparable

Deepseek Coder v2: 37.0 (#224), Qwen3.7 Flash: —

BenchmarkDeepseek Coder v2Qwen3.7 Flash
LMArena Longer Query1219—

Writing & Preference Not comparable

Deepseek Coder v2: 38.2 (#253), Qwen3.7 Flash: —

BenchmarkDeepseek Coder v2Qwen3.7 Flash
LMArena Text1191—
LMArena Creative Writing1120—
LMArena Multi-Turn1177—

Frequently asked questions

Is Deepseek Coder v2 better than Qwen3.7 Flash?

Qwen3.7 Flash is the stronger model overall, scoring 39.9 to 35.9 on the Noometry Index.

How many benchmarks do Deepseek Coder v2 and Qwen3.7 Flash share?

0 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Qwen3.7 Flash has 7.

Related comparisons

Go deeper