Which is better, Claude Sonnet 4.6 or Qwen3.5 2B?

Claude Sonnet 4.6 vs Qwen3.5 2B

20 SHARED BENCHMARKS

Across 20 shared benchmarks, Claude Sonnet 4.6 scores higher on 20 and Qwen3.5 2B on 0. The widest gap is HLE, where Claude Sonnet 4.6 scores 49 against 5.

ANTHROPICVSALIBABA20 SHARED20–0 HEAD-TO-HEAD

BenchmarkClaude Sonnet 4.6MARGINQwen3.5 2B

AA Agentic Index61.60.8

AA Intelligence30.56.9

AA-LCR8025.6

AA-Omniscience12.2-60.2

Artificial Analysis Coding Index632.9

critpt3.10

gdpval54.80

GPQA Diamond89.951.6

HLE495

IFBench56.641.3

mmmlu89.363.1

MMMU-Pro75.643

OmniScience Accuracy40.98.1

OmniScience Non-Hallucination51.625.8

scicode50.17.2

TauBench V3 - Banking34.42.5

Terminal-Bench 2.171.23

Terminal-Bench Hard59.13.8

τ²-Bench Telecom (AA run)97.981.6

τ³-Bench30.56.2

Best tracked score per model per benchmark (default configuration; source-attributed). ↓ marks lower-is-better metrics. Open either model for its full surface, provenance and pricing.

Compare Claude Sonnet 4.6 withALL PAIRINGS →

AnthropicClaude Opus 4.8 Claude Opus 4.6 Claude Sonnet 4.5 Claude 3.5 Sonnet Claude Fable 5 Claude Opus 4.5

Across the fieldQwen3.6 27B Qwen3.7 Max Qwen3.8 Max Preview Qwen3.7 Plus Preview Claude Opus 4 Qwen3.5 4B Gemini 3.6 Flash Nemotron 3 Super 120B A12B

Compare Qwen3.5 2B withALL PAIRINGS →

AlibabaQwen3.5 35B A3B Qwen3 VL 4B (Reasoning)Qwen3.5 397B A17B Qwen2.5 Instruct 72B Qwen3.5 27B Qwen3.6 Plus

Across the fieldo1 Gemma 4 31B Kimi K2 Instruct Gemma 4 E2B GPT-4o mini Qwen3.6 35B A3B Gemini 3.5 Flash GPT-6 Astra