Noometry

Model comparison

Qwen3.6 Max Preview vs StarCoder 2 15B

Qwen3.6 Max Preview has enough public results to be ranked (#36); StarCoder 2 15B does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

Qwen3.6 Max Preview Alibaba (Qwen)

51.1

Rank #36 Confirmed

StarCoder 2 15B NVIDIA

37.5

Unranked Sparse

Summary

  • They share 1 benchmark with published results for both. Qwen3.6 Max Preview scores higher in 1 category and StarCoder 2 15B in 0 categories; one gap is clear of the uncertainty.
  • The widest gap is in coding, where Qwen3.6 Max Preview leads 48.6 to 36.0.
  • StarCoder 2 15B has downloadable open weights; the other is API-only.

Side by side

Qwen3.6 Max PreviewStarCoder 2 15B
ProviderAlibaba (Qwen)NVIDIA
Noometry Index51.137.5
Released2026-04-202024-02-20
WeightsProprietaryOpen
Context window262K—
Max output66K—
Input $ / M tokens$1.30—
Output $ / M tokens$7.80—
Results tracked297

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

Category by category

Coding Qwen3.6 Max Preview leads

Qwen3.6 Max Preview: 48.6 (#50), StarCoder 2 15B: 36.0

BenchmarkQwen3.6 Max PreviewStarCoder 2 15B
SWE-bench Verified76.7%—
LMArena WebDev1482—
LMArena Coding1472—
BigCodeBench Complete—38.4%
HumanEval+—37.8%

Agentic & Tool Use Not comparable

Qwen3.6 Max Preview: —, StarCoder 2 15B: —

BenchmarkQwen3.6 Max PreviewStarCoder 2 15B
Vending-Bench 24,254—

Reasoning Not comparable

Qwen3.6 Max Preview: 40.8 (#47), StarCoder 2 15B: —

BenchmarkQwen3.6 Max PreviewStarCoder 2 15B
Epoch Capabilities Index149.27104.61
SimpleBench63%—
NYT Connections (extended)74.1%—
Chess Puzzles20%—
LMArena Hard Prompts1457—
Mystery Game Puzzles19%—
DTBench87.2%—
LMCA42.5%—
WinoGrande—64.3%

Math Not comparable

Qwen3.6 Max Preview: 52.2 (#40), StarCoder 2 15B: —

BenchmarkQwen3.6 Max PreviewStarCoder 2 15B
OTIS Mock AIME 2024-202591.1%—
LMArena Math1465—
FrontierMath (Feb 2025 set)23.1%—
FrontierMath Tier 4 (v1)4.2%—
GSM8K—57.7%

Knowledge Not comparable

Qwen3.6 Max Preview: 57.6 (#35), StarCoder 2 15B: —

BenchmarkQwen3.6 Max PreviewStarCoder 2 15B
GPQA Diamond87.4%—
SimpleQA Verified52%—
LMArena Expert1476—
ARC (AI2) Challenge—47.2%
MMLU—64.1%

Multilingual Not comparable

Qwen3.6 Max Preview: 54.3 (#46), StarCoder 2 15B: —

BenchmarkQwen3.6 Max PreviewStarCoder 2 15B
LMArena Non-English1436—
LMArena Chinese1487—
LMArena French1449—
LMArena Russian1444—
LMArena Spanish1452—

Instruction Following Not comparable

Qwen3.6 Max Preview: 75.8 (#51), StarCoder 2 15B: —

BenchmarkQwen3.6 Max PreviewStarCoder 2 15B
LMArena Instruction Following1437—

Long Context Not comparable

Qwen3.6 Max Preview: 44.6 (#59), StarCoder 2 15B: —

BenchmarkQwen3.6 Max PreviewStarCoder 2 15B
LMArena Longer Query1457—

Writing & Preference Not comparable

Qwen3.6 Max Preview: 64.0 (#58), StarCoder 2 15B: —

BenchmarkQwen3.6 Max PreviewStarCoder 2 15B
LMArena Text1447—
LMArena Creative Writing1435—
LMArena Multi-Turn1456—

Frequently asked questions

Is Qwen3.6 Max Preview better than StarCoder 2 15B?

Qwen3.6 Max Preview has enough public results to be ranked (#36); StarCoder 2 15B does not yet, so treat this comparison as directional.

Is Qwen3.6 Max Preview or StarCoder 2 15B better for coding?

Qwen3.6 Max Preview scores higher on coding benchmarks: 48.6 versus 36.0 in the Noometry coding category.

How many benchmarks do Qwen3.6 Max Preview and StarCoder 2 15B share?

1 benchmark has published results for both models. Qwen3.6 Max Preview has 29 scored results on Noometry and StarCoder 2 15B has 7.

Related comparisons

Go deeper