โ† Back to Model Hub/SIDE-BY-SIDE REVIEW
SHARE THIS:

MiniMax M2.7 vs Mistral Small 3.1 24B

How do these models stack up? Below is an expert side-by-side comparison of specifications, context window capacity, live pricing per million tokens, and standardized benchmark scores for MiniMax M2.7 and Mistral Small 3.1 24B.

MiniMax

MiniMax M2.7

MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...

View Full Specs
Mistral

Mistral Small 3.1 24B

Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...

View Full Specs

Technical Specifications

SpecificationMiniMax M2.7Mistral Small 3.1 24B
ProviderMiniMaxMistral
Context Window204,800 tokens128,000 tokens
Agent SuitabilityN/AN/A
Time to First Token (TTFT)N/AN/A
Deployment Modelmanaged apiself hostable
Production Stabilitystablestable
API AvailableYesYes
Released Date2026-03-182025-03-17

API Pricing Comparison

Input Price per Million Tokens

MiniMax M2.7

$0.18

Mistral Small 3.1 24B

$0.35

Output Price per Million Tokens

MiniMax M2.7

$0.72

Mistral Small 3.1 24B

$0.56

Want to test both models live?

Run side-by-side prompt prompts in our dynamic Sandbox. Check execution speeds, latency metrics, and compute actual costs in real-time.

Benchmark Performance Metrics

Scores show the raw performance percentages verified across key evaluation suites. Higher bars indicate superior accuracy and capability in that domain.

MMLUGeneral knowledge & multi-task understanding
8250.0%vsN/A
MiniMax M2.7
Mistral Small 3.1 24B
HumanEvalPython coding & logic synthesis
8000.0%vsN/A
MiniMax M2.7
Mistral Small 3.1 24B
MATHComplex mathematical problem solving
5400.0%vsN/A
MiniMax M2.7
Mistral Small 3.1 24B
GPQAGraduate-level expert reasoning
3900.0%vsN/A
MiniMax M2.7
Mistral Small 3.1 24B
HellaSwagCommonsense reasoning and inference
8400.0%vsN/A
MiniMax M2.7
Mistral Small 3.1 24B
MT-BenchMulti-turn conversation flow quality
870.0%vsN/A
MiniMax M2.7
Mistral Small 3.1 24B

MiniMax M2.7 Quirks & Gotchas

No developer gotchas reported.

Mistral Small 3.1 24B Quirks & Gotchas

No developer gotchas reported.