head-to-head

Mistral: Mistral Small 4 vs MoonshotAI: Kimi K2.5

Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-09-23.

Mistral: Mistral Small 4 MoonshotAI: Kimi K2.5
Vendormistralaimoonshotai
Quality Score100100
Benchmark Score3.859.2
Input Price$0.15/M$0.45/M
Output Price$0.60/M$2.25/M
Context Window262,144262,144
Max Output209,715235,929
Tool Calling
Structured Output
Reasoning Mode
Vision
Audio--
Benchmark Scores
ai_index9.638.7
eqbench-72.5

Who wins by task?

TaskMistral: Mistral Small 4MoonshotAI: Kimi K2.5
SQL Generation 132 140
Code Review 128 142
Code Completion 129 131
Code Refactoring 129 143
Bug Fixing 132 146
Unit Test Generation 122 131
Code Documentation 127 135
Regex Writing 120 126
CI/CD Pipelines 118 127
Frontend Component Design 123 129
Data Analysis 125 134
CSV / Spreadsheet Cleanup 128 134
ETL Scripting 123 135
JSON Extraction 131 131
Bulk Data Labeling 129 129
OCR / Document Parsing 128 132
Table Extraction from PDFs 128 132
Long-Document Summarization 131 145
Short-Form Summarization 124 126
Blog Post Writing 120 128

Scores reflect capability match + benchmark data + pricing for each task. Methodology →

Related comparisons

Anthropic: Claude Haiku Latest vs Mistral: Mistral Small 4 Anthropic: Claude Haiku Latest vs MoonshotAI: Kimi K2.5 Anthropic: Claude Sonnet 5 vs Mistral: Mistral Small 4 Anthropic: Claude Sonnet Latest vs Mistral: Mistral Small 4 ByteDance Seed: Seed-2.0-Mini vs MoonshotAI: Kimi K2.5 Google: Gemini 3.1 Pro Preview vs MoonshotAI: Kimi K2.5 Google: Gemini 3.5 Flash vs Mistral: Mistral Small 4 Google: Gemini Flash Latest vs Mistral: Mistral Small 4

The Model Movers Report

One email every Friday, built from this site's own rankings: the current top five by benchmark score, every model released in the last seven days, and one note worked out from that week's numbers. You can unsubscribe from any issue with one click.