Which is better, Kimi K2.5 or Qwen3.5 2B?

Kimi K2.5 vs Qwen3.5 2B

27 SHARED BENCHMARKS

Across 27 shared benchmarks, Kimi K2.5 scores higher on 27 and Qwen3.5 2B on 0. The widest gap is Terminal-Bench Hard, where Kimi K2.5 scores 34.8 against 3.8.

MOONSHOTVSALIBABA27 SHARED27–0 HEAD-TO-HEAD

BenchmarkKimi K2.5MARGINQwen3.5 2B

AA Agentic Index52.80.8

AA Intelligence23.56.9

AA-LCR7825.6

AA-Omniscience-7.3-60.2

AIME 202596.119

Artificial Analysis Coding Index46.82.9

critpt3.10

gdpval38.30

Global-MMLU-Lite8464.5

GPQA Diamond87.951.6

HLE50.25

IFBench70.241.3

longbench_v26138.7

MathVista90.148.7

MMLU-Pro87.166.5

MMMU-Pro78.543

multichallenge61.433.7

OCRBench92.386.1

OmniScience Accuracy35.28.1

OmniScience Non-Hallucination5025.8

scicode497.2

SimpleVQA71.235.2

TauBench V3 - Banking14.22.5

Terminal-Bench 2.145.73

Terminal-Bench Hard34.83.8

τ²-Bench Telecom (AA run)95.981.6

τ³-Bench666.2

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 Kimi K2.5 withALL PAIRINGS →

MoonshotKimi K2.6 Kimi K3 Kimi K2 Instruct

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 fieldo3 GPT-5.1 Claude Opus 5 Gemma 4 26B A4B Kimi K3 Llama 3.1 Instruct 405B DeepSeek-V3.2 DeepSeek-V4-Flash