Noometry

Model comparison

Qwen3.5 397B-A17B vs Sonar

Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 38.5 on the Noometry Index.

Last verified . 0 shared benchmarks.

Qwen3.5 397B-A17B Alibaba (Qwen)

46.0

Rank #67 Confirmed

Sonar Perplexity

38.5

Rank #187 Confirmed

Summary

  • The widest gap is in reasoning, where Qwen3.5 397B-A17B leads 34.5 to 21.1.
  • Sonar is cheaper at $1 / $1 per million input/output tokens, against $0.60 / $3.60 for Qwen3.5 397B-A17B.
  • Qwen3.5 397B-A17B accepts more context: 262K tokens versus 128K.
  • Qwen3.5 397B-A17B has downloadable open weights; the other is API-only.

Side by side

Qwen3.5 397B-A17BSonar
ProviderAlibaba (Qwen)Perplexity
Noometry Index46.038.5
Released2026-02-012024-01-01
WeightsOpenProprietary
Context window262K128K
Max output66K4K
Input $ / M tokens$0.60$1
Output $ / M tokens$3.60$1
Results tracked367

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

Category by category

Coding Qwen3.5 397B-A17B leads

Qwen3.5 397B-A17B: 42.0 (#114), Sonar: 35.7 (#221)

BenchmarkQwen3.5 397B-A17BSonar
LMArena WebDev1400—
LiveBench Coding—35.1%
LMArena Coding1465—

Agentic & Tool Use Not comparable

Qwen3.5 397B-A17B: 33.3 (#53), Sonar: —

BenchmarkQwen3.5 397B-A17BSonar
APEX-Agents24.9%—
τ²-bench Airline81.5%—
τ²-bench Banking9.8%—
τ²-bench Retail84.4%—
τ²-bench Telecom97.8%—

Reasoning Qwen3.5 397B-A17B leads

Qwen3.5 397B-A17B: 34.5 (#70), Sonar: 21.1 (#227)

BenchmarkQwen3.5 397B-A17BSonar
Kagi LLM Benchmark73.7%—
NYT Connections (extended)58.9%—
Chess Puzzles13%—
Thematic Generalization65.1%—
LiveBench Reasoning—46.3%
LMArena Hard Prompts1448—
Mystery Game Puzzles18%—
DTBench87.5%—
LiveBench Data Analysis—37.9%
LMCA37.9%—
Epoch Capabilities Index146.65—
LiveBench—46.9%

Math Qwen3.5 397B-A17B leads

Qwen3.5 397B-A17B: 46.1 (#73), Sonar: 33.7 (#200)

BenchmarkQwen3.5 397B-A17BSonar
FrontierMath (Tiers 1-3)31.2%—
OTIS Mock AIME 2024-202588.9%—
LiveBench Math—41.6%
LMArena Math1454—

Knowledge Not comparable

Qwen3.5 397B-A17B: 53.3 (#58), Sonar: —

BenchmarkQwen3.5 397B-A17BSonar
GPQA Diamond86.4%—
LMArena Expert1462—

Multimodal Not comparable

Qwen3.5 397B-A17B: 40.7 (#44), Sonar: —

BenchmarkQwen3.5 397B-A17BSonar
LMArena Vision1263—

Multilingual Not comparable

Qwen3.5 397B-A17B: 53.7 (#59), Sonar: —

BenchmarkQwen3.5 397B-A17BSonar
LMArena Non-English1430—
LMArena Chinese1500—
LMArena French1461—
LMArena German1447—
LMArena Japanese1426—
LMArena Korean1384—
LMArena Russian1429—
LMArena Spanish1441—

Instruction Following Qwen3.5 397B-A17B leads

Qwen3.5 397B-A17B: 75.0 (#77), Sonar: 71.4 (#150)

BenchmarkQwen3.5 397B-A17BSonar
LiveBench Instruction Following—76.2%
LMArena Instruction Following1424—

Long Context Not comparable

Qwen3.5 397B-A17B: 44.1 (#74), Sonar: —

BenchmarkQwen3.5 397B-A17BSonar
LMArena Longer Query1442—

Writing & Preference Qwen3.5 397B-A17B leads

Qwen3.5 397B-A17B: 62.3 (#79), Sonar: 52.6 (#167)

BenchmarkQwen3.5 397B-A17BSonar
LMArena Text1438—
LMArena Creative Writing1401—
EQ-Bench Creative Writing1478—
LMArena Multi-Turn1446—
LiveBench Language—44.1%

Frequently asked questions

Is Qwen3.5 397B-A17B better than Sonar?

Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 38.5 on the Noometry Index.

Which is cheaper, Qwen3.5 397B-A17B or Sonar?

Sonar is cheaper. It lists at $1 per million input tokens and $1 per million output tokens; Qwen3.5 397B-A17B lists at $0.60 and $3.60.

Is Qwen3.5 397B-A17B or Sonar better for coding?

Qwen3.5 397B-A17B scores higher on coding benchmarks: 42.0 versus 35.7 in the Noometry coding category.

Which has the bigger context window?

Qwen3.5 397B-A17B does, with 262K tokens against 128K.

How many benchmarks do Qwen3.5 397B-A17B and Sonar share?

0 benchmarks have published results for both models. Qwen3.5 397B-A17B has 36 scored results on Noometry and Sonar has 7.

Related comparisons

Go deeper