Noometry

Model comparison

Qwen3.6 27B vs Qwen3.8 27B

Qwen3.8 27B is the stronger model overall, scoring 46.0 to 42.2 on the Noometry Index.

Last verified . 5 shared benchmarks.

Qwen3.6 27B Alibaba (Qwen)

42.2

Rank #117 Confirmed

Qwen3.8 27B Alibaba (Qwen)

46.0

Rank #68 Confirmed

Summary

  • They share 5 benchmarks with published results for both. Qwen3.6 27B scores higher in 2 categories and Qwen3.8 27B in 3 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Qwen3.8 27B leads 41.0 to 25.0.
  • The biggest single-benchmark swing is DTBench: 78.1% for Qwen3.6 27B and 88% for Qwen3.8 27B.
  • Qwen3.8 27B is cheaper at $0.99 / $1.49 per million input/output tokens, against $0.60 / $3.60 for Qwen3.6 27B.

Side by side

Qwen3.6 27BQwen3.8 27B
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index42.246.0
Released2026-04-222026-08-14
WeightsOpenOpen
Context window262K262K
Max output66K33K
Input $ / M tokens$0.60$0.99
Output $ / M tokens$3.60$1.49
Results tracked1131

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

Category by category

Coding Qwen3.8 27B leads

Qwen3.6 27B: 39.1 (#163), Qwen3.8 27B: 50.5 (#44)

BenchmarkQwen3.6 27BQwen3.8 27B
SciCode37.3%46.6%
LMArena WebDev—1593
LMArena Coding—1482

Agentic & Tool Use Not comparable

Qwen3.6 27B: —, Qwen3.8 27B: 32.9 (#57)

BenchmarkQwen3.6 27BQwen3.8 27B
APEX-Agents—47.5%

Reasoning Qwen3.8 27B leads

Qwen3.6 27B: 25.0 (#153), Qwen3.8 27B: 41.0 (#54)

BenchmarkQwen3.6 27BQwen3.8 27B
CritPt0.9%5.4%
DTBench78.1%88%
LMCA34.5%41.4%
Epoch Capabilities Index146.5149.38
ARC-AGI-2—42.4%
NYT Connections (extended)—54.5%
ARC-AGI-1—87.5%
Chess Puzzles22%—
LMArena Hard Prompts—1460
Mystery Game Puzzles7%—
Surface Evolver Bench—45%

Math Qwen3.6 27B leads

Qwen3.6 27B: 48.5 (#62), Qwen3.8 27B: 37.1 (#161)

BenchmarkQwen3.6 27BQwen3.8 27B
FrontierMath (Tiers 1-3)35.1%—
OTIS Mock AIME 2024-202591.1%—
ProofBench—16%
LMArena Math—1456

Knowledge Qwen3.6 27B leads

Qwen3.6 27B: 52.4 (#63), Qwen3.8 27B: 41.6 (#109)

BenchmarkQwen3.6 27BQwen3.8 27B
GPQA Diamond85.9%—
LMArena Expert—1482

Multimodal Not comparable

Qwen3.6 27B: —, Qwen3.8 27B: 41.3 (#37)

BenchmarkQwen3.6 27BQwen3.8 27B
LMArena Vision—1271

Multilingual Not comparable

Qwen3.6 27B: —, Qwen3.8 27B: 53.7 (#60)

BenchmarkQwen3.6 27BQwen3.8 27B
LMArena Non-English—1430
LMArena Chinese—1504
LMArena French—1465
LMArena German—1438
LMArena Japanese—1384
LMArena Korean—1393
LMArena Russian—1415
LMArena Spanish—1448

Instruction Following Not comparable

Qwen3.6 27B: —, Qwen3.8 27B: 75.8 (#53)

BenchmarkQwen3.6 27BQwen3.8 27B
LMArena Instruction Following—1439

Long Context Not comparable

Qwen3.6 27B: —, Qwen3.8 27B: 44.3 (#70)

BenchmarkQwen3.6 27BQwen3.8 27B
LMArena Longer Query—1450

Writing & Preference Qwen3.8 27B leads

Qwen3.6 27B: 50.3 (#181), Qwen3.8 27B: 65.8 (#43)

BenchmarkQwen3.6 27BQwen3.8 27B
LMArena Text—1441
LMArena Creative Writing—1384
EQ-Bench Creative Writing—1671
EQ-Bench 41026—
LMArena Multi-Turn—1441

Frequently asked questions

Is Qwen3.6 27B better than Qwen3.8 27B?

Qwen3.8 27B is the stronger model overall, scoring 46.0 to 42.2 on the Noometry Index.

Which is cheaper, Qwen3.6 27B or Qwen3.8 27B?

Qwen3.8 27B is cheaper. It lists at $0.99 per million input tokens and $1.49 per million output tokens; Qwen3.6 27B lists at $0.60 and $3.60.

Is Qwen3.6 27B or Qwen3.8 27B better for coding?

Qwen3.8 27B scores higher on coding benchmarks: 50.5 versus 39.1 in the Noometry coding category.

Which has the bigger context window?

Both accept 262K tokens.

How many benchmarks do Qwen3.6 27B and Qwen3.8 27B share?

5 benchmarks have published results for both models. Qwen3.6 27B has 11 scored results on Noometry and Qwen3.8 27B has 31.

Related comparisons

Go deeper