Mistral Large
Feb 2024
Mistral LargeCompare inon
Mistral Large measured on 16 of 109 Chat & Knowledge benchmarks16
BenchmarkByScoreRank
Overall1
Knowledge13
Science1
Legacy · saturated or no longer reported1
No benchmark matches
Rankingin non-thinking mode?
Full ranking →···
168Qwen1,292.5169Mistral Large1,283.9170Qwen2.5 72B Instruct1,282.5Strong at
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperMiMo v2.6 ProunstatedOpenwins 78%-82%$0.43 / $0.87Pass back reasoning_content+3
BetterGPT-5 Minihighwins 63%-77%$0.053
CheaperGemini 3.8 Flashhighwins 77%-50%*$3.49Sampling parameters are ignored+1
CheaperMuse Spark 1.3maxwins 77%-33%$3.69Only auto tool_choice is supported+5CheaperMuse Spark 1.2xhighwins 76%-33%$1.29Only auto tool_choice is supported+1ModelScoreCostPer taskWhat changes
MiMo v2.6 ProunstatedOpenwins 78%-82%$0.43 / $0.87Pass back reasoning_content+3Gemini 3.8 Flashhighwins 77%-50%*$3.49Sampling parameters are ignored+1Muse Spark 1.3maxwins 77%-33%$3.69Only auto tool_choice is supported+5Muse Spark 1.2xhighwins 76%-33%$1.29Only auto tool_choice is supported+1
GLM 5.3maxOpenwins 76%-28%$2.01Reasoning cannot be disabled+3ModelScoreCostPer taskWhat changes
GPT-5 Minihighwins 63%-77%$0.053GPT-6 Lunamaxwins 65%-93%$0.068Function calling only with none · Chat Completions+3
Claude Haiku 5.5highwins 67%-93%$0.079Remove sampling parameters+5GPT-5.6 Lunaxhighwins 71%-85%$0.085GPT-5.6 Terraxhighwins 72%+50%$0.63Prompts with >272K input tokensModelScoreCostPer taskWhat changes
MiMo v2.6 ProunstatedOpenwins 78%-82%$0.43 / $0.87Pass back reasoning_content+3GLM 5.3maxOpenwins 76%-28%$2.01Reasoning cannot be disabled+3
Kimi K3maxOpenwins 76%+100%$2.00Sampling parameters are fixed+3MiMo v2.5 ProunstatedOpenwins 75%-82%$0.43 / $0.87GLM 5.1unstatedOpenwins 75%-28%$1.40 / $4.40ModelScoreCostPer taskWhat changes
Mistral Large 3unstatedOpenwins 71%—$0.50 / $1.50Mistral Large 4unstatedwins 70%—$1.36 / $4.18Infinite whitespace stream+4Mistral Medium 3.5unstatedOpenwins 70%—$1.50 / $7.50Mistral Small 3.1 24BunstatedOpensame—$0.35 / $0.56Mistral Small 3unstatedOpenwins 46%—$0.05 / $0.08Context: 128K → 32KMixtral 8x22B InstructunstatedOpenwins 36%—$2 / $6Context: 128K → 66KMixtral 8x7B Instruct v0.1Openwins 34%—$0.54 / $0.54Context: 128K → 33KMistral 7B Instruct v0.2Openwins 30%—$0.055 / $0.055Context: 128K → 33K+1All Mistral models →History
4 versionsBenchmarks
in Chat & KnowledgeAA Intelligence Index 4.3.2≈5.8#304
Humanity's Last Exam3.5#330
GPQA Diamond35.1#288
FAQ
How much does Mistral Large cost?›
$2 per 1M input tokens and $6 per 1M output tokens; cached input $0.20 per 1M.
Is Mistral Large free to use?›
There is no free API; the cheapest paid price is $2 per 1M input tokens.
How good is Mistral Large, and what is it best at?›
#327 of 336 in Chat & Knowledge, #138 of 152 in Coding, #156 of 197 in Writing & Language.
Is Mistral Large better than Qwen?›
On Arena Text · English, Mistral Large scores 1,283.9 vs 1,292.5 — about the same.
How can I use Mistral Large?›
Through the API of AWS Bedrock, Mistral.
What is the context window of Mistral Large?›
128K tokens, with up to 102K output tokens.
When was Mistral Large released? Is there a newer version?›
Released 2024-02-26. It has been superseded by Mistral Large 2407.
Is Mistral Large open source?›
No, Mistral Large is a closed model available through an API. The closest open-weights option here is MiMo v2.6 Pro.
Can Mistral Large read images?›
It accepts text and PDF files as input.
What is Mistral Large?›
Mistral Large is a closed language model from Mistral, released Feb 2024.
What are the best alternatives to Mistral Large?›
MiMo v2.6 Pro (cheaper), GPT-5 Mini (better).