GitHub[208K]Try OpenCode

Compare AI models: MAI-Code-1.1-Flash vs Mistral Large 4

  1. MAI-Code-1.1-FlashMicrosoftHollow points use fallbacks · hover for details
  2. Mistral Large 4MistralHollow points use fallbacks · hover for details
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
MAI-Code-1.1-Flash50/100 — Reasoning supported; no comparable benchmark50/100 — No data; neutral placeholder61/10052/10033/10050/100 — Tool calling supported; no comparable benchmark
Mistral Large 450/100 — Reasoning supported; no comparable benchmark50/100 — No data; neutral placeholder49/10092/10033/10050/100 — Tool calling supported; no comparable benchmark
Overview
Author
Context length
256K
1M
Reasoning
True
True
Input modalities
Text, Image
Text, Image
Output modalities
Text
Text
Providers
Pricing
Input
$0.20/ 1M
$0.68/ 1M
Output
$1.20/ 1M
$2.09/ 1M
Cached input
$0.02/ 1M
$0.07/ 1M
MomentumLast 2 mo
Unique users
No usage
No usage
Completed sessions
No usage
No usage
Token share
No usage
No usage
Tokens
No usage
No usage
No trend data
No trend data
RetentionWeek 1
Returning users
Pending
Pending

Related comparisons. Other model pairs to check.