Claude Haiku 4.5vsMistral Medium 3.5

Claude Haiku 4.5
Mistral Medium 3.5
Specifications
Parameters
128B
Context window
256k
API pricing
Input price
$1.00$1.50
Output price
$5.00$7.50
Cached input price
$0.10
Cheapest input
$1.00Amazon Bedrock
Cheapest output
$5.00Amazon Bedrock
Benchmarks
SWE-Bench Verified
73.3%77.6%
Benchmarks
BullshitBench v2
77%
ProgramBench
0%
GPQA Diamond
73%
Overview
CompanyAnthropicMistral
Release dateOct 15 2025Apr 29 2026
AccessProprietaryOpen Weight

Other comparisons

Claude Haiku 4.5vsGPT-6 AstraMistral Medium 3.5vsGPT-6 AstraClaude Haiku 4.5vsGemini 3.8 FlashMistral Medium 3.5vsGemini 3.8 FlashClaude Haiku 4.5vsMuse Spark 1.3Mistral Medium 3.5vsMuse Spark 1.3Claude Haiku 4.5vsGrok 4.6Mistral Medium 3.5vsGrok 4.6Claude Haiku 4.5vsDeepSeek-V4.1-FlashMistral Medium 3.5vsDeepSeek-V4.1-FlashClaude Haiku 4.5vsKimi K3Mistral Medium 3.5vsKimi K3

Frequently asked questions

Mistral Medium 3.5 leads Claude Haiku 4.5 on 1 of the 1 benchmark they both report (SWE-Bench Verified). Claude Haiku 4.5 is cheaper on both input and output: $1.00 vs $1.50 per million input tokens, and $5.00 vs $7.50 per million output tokens. Claude Haiku 4.5 shipped 196 days before Mistral Medium 3.5, so benchmark comparisons should account for the intervening progress.

Claude Haiku 4.5 is proprietary, while Mistral Medium 3.5 is open weight.

On SWE-Bench Verified, Mistral Medium 3.5 leads at 77.6% vs Claude Haiku 4.5 at 73.3%.