Mistral Small 3.1 (25.03)
Mistral Small 3.1 (25.03)Compare inon
Mistral Small 3.1 (25.03) measured on 2 of 109 Chat & Knowledge benchmarks2
BenchmarkByScoreRank
Legacy · saturated or no longer reported2
No benchmark matches
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperQwen3.7 Flashunstated+96%-63%$0.03 / $0.13
BetterGPT-5.6 Lunalow+96%+200%$0.01
OpenDeepSeek V4.1 Flash 1017max×2.2+250%$0.26Pass back reasoning_content · Chat Completions+4CheaperQwen 3.5 Flashunstated+96%-24%$0.065 / $0.26CheaperQwen 3.5 9BunstatedOpen+88%-38%$0.08 / $0.13ModelScoreCostPer taskWhat changes
Qwen3.7 Flashunstated+96%-63%$0.03 / $0.13Qwen 3.5 Flashunstated+96%-24%$0.065 / $0.26Qwen 3.5 9BunstatedOpen+88%-38%$0.08 / $0.13GPT OSS 120BhighOpen+81%-60%$0.11GPT-5 Nano (2025-08-07)high+66%-8%$0.05 / $0.40ModelScoreCostPer taskWhat changes
GPT-5.6 Lunalow+96%+200%$0.01GPT OSS 20BhighOpen+10%-76%$0.011
Gemini 3.1 Flash Litehigh+95%+275%$0.06GPT-6 Lunamax×2.2+33%$0.068Function calling only with none · Chat Completions+3GPT OSS 120BhighOpen+81%-60%$0.11ModelScoreCostPer taskWhat changes
DeepSeek V4.1 Flash 1017maxOpen×2.2+250%$0.26Pass back reasoning_content · Chat Completions+4
Kimi K3maxOpen×2.2+3,900%$2.00Sampling parameters are fixed+3
GLM 5.2maxOpen×2.2+1,333%$1.28DeepSeek V4 Pro 0813maxOpen×2.2+1,220%$0.67Pass back reasoning_content · Chat Completions+4
MiniMax M3unstatedOpen×2.2+250%$0.30 / $1.20Deployment status experimental · Self-hostedModelScoreCostPer taskWhat changes
Mistral Large 4high×2.1—$1.36 / $4.18Infinite whitespace stream+4Magistral Small 1unstatedOpen+34%—$0.70 / $1.16Mixtral 8x7B Instruct v0.1Open-27%—$0.54 / $0.54Mistral 7B Instruct v0.3Open-64%—$0.028 / $0.054Mistral Medium 3.5highOpenn/a—$0.43Mistral Small 4thinkingOpenn/a—$0.017Ministral 3 14B 2512non-thinkingOpenn/a—$0.019Ministral 3 3B 2512Openn/a—$0.008All Mistral models →FAQ
How much does Mistral Small 3.1 (25.03) cost?›
$0.10 per 1M input tokens and $0.30 per 1M output tokens (cheapest host: Google Vertex AI).
Is Mistral Small 3.1 (25.03) free to use?›
There is no free API; the cheapest paid price is $0.10 per 1M input tokens.
How good is Mistral Small 3.1 (25.03), and what is it best at?›
#112 of 134 in Chat & Knowledge.
Is Mistral Small 3.1 (25.03) better than WizardLM 2 8x22B?›
On GPQA Diamond · Epoch, Mistral Small 3.1 (25.03) scores 41.9 vs 43.4 — lower.
How can I use Mistral Small 3.1 (25.03)?›
Through the Mistral API.
What is Mistral Small 3.1 (25.03)?›
Mistral Small 3.1 (25.03) is a language model from Mistral.
What are the best alternatives to Mistral Small 3.1 (25.03)?›
Qwen3.7 Flash (cheaper), GPT-5.6 Luna (better), DeepSeek V4.1 Flash 1017 (open weights).