head-to-head

Mistral: Mistral Medium 3.5 vs Anthropic: Claude Haiku Latest

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

	Mistral: Mistral Medium 3.5	Anthropic: Claude Haiku Latest
Vendor	mistralai	~anthropic
Quality Score	100	100
Benchmark Score	19.3	-
Input Price	$1.50/M	$1.00/M
Output Price	$7.50/M	$5.00/M
Context Window	262,144	200,000
Max Output	209,715	64,000
Tool Calling	✓	✓
Structured Output	✓	✓
Reasoning Mode	✓	✓
Vision	✓	✓
Audio	-	-
Benchmark Scores
ai_index	23.4	-

Who wins by task?

Task	Mistral: Mistral Medium 3.5	Anthropic: Claude Haiku Latest
SQL Generation	133	129
Code Review	130	124
Code Completion	115	114
Code Refactoring	131	124
Bug Fixing	134	128
Unit Test Generation	124	120
Code Documentation	126	122
Regex Writing	120	118
CI/CD Pipelines	120	116
Frontend Component Design	124	122
Data Analysis	127	124
CSV / Spreadsheet Cleanup	128	125
ETL Scripting	125	120
JSON Extraction	122	122
Bulk Data Labeling	119	120
OCR / Document Parsing	129	127
Table Extraction from PDFs	129	127
Long-Document Summarization	132	125
Short-Form Summarization	115	114
Blog Post Writing	121	117

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