Skip to main content

Compare Leaderboards Agents Insights

Loading...

Compare LLM models by quality, speed, and price. Find the right model for your use case.

Product

Explore Models
Compare
Leaderboards
LLM Selector
Cost Calculator
Provider Finder

Resources

Insights
FAQ
About
Methodology

Data Sources

Data from Artificial Analysis, OpenRouter, HuggingFace, and other public sources.

© 2026 FindLLM. All rights reserved.

Devstral Small 2 — Mistral | FindLLM

Home
Explore
Devstral Small 2

Back to Explore

Devstral Small 2

Mistral·Released 2025-12-09

Open Source

Related Models

Devstral 22025-12-09 Mistral: Devstral 2 25122025-12-09 Mistral: Devstral Medium2025-07-10 Mistral: Devstral Small 1.12025-07-10 Devstral Small (May '25)2025-05-21

Performance

60

tokens/sec

Faster than 29% of models

0.57

seconds

Faster than 77% of models

0.57

seconds

Faster than 84% of models

Market Median

86 tok/s

30% slower

Median TTFT

1.07s

47% faster

Speed Comparison

OpenAI: GPT-4o-mini

60 tok/s-0%

Qwen3 235B A22B 2507 (Reasoning)

60 tok/s-1%

MiMo-V2.5-Pro (Non-reasoning)

61 tok/s+1%

Benchmarks

MMLU-Pro

67.8%

GPQA Diamond

53.2%

HLE

3.4%

LiveCodeBench

34.8%

SciCode

28.8%

TerminalBench Hard

16.7%

MATH-500Not evaluated

AIMENot evaluated

AIME 2025

34.3%

IFBench

31.2%

Long Context Recall

24.0%

Tau2

23.4%

Market AverageTop Score

Open Source

Quick Compare

Similar Models

Google: Gemini 2.5 Flash Lite Preview 09-2025

Google

Q: 19.4$0.17/1M1.0M ctx

Faster: 486%Coding: -6.2

Gemini 2.0 Flash Thinking Experimental (Jan '25)

Google

QwQ 32B

Alibaba

Q: 19.7$0.74/1M131K ctx

Qwen3 VL 30B A3B (Reasoning)

Alibaba

Q: 19.7$0.34/1M

Faster: 109%Coding: -7.6

Qwen3 235B A22B (Reasoning)

Alibaba

Q: 19.8$2.63/1M

Motif-2-12.7B-Reasoning

Motif Technologies

Compare all 7 models

Quality Index

19.5

250th of 507

Top 49%

Coding Index

20.7

194th of 417

Top 47%

Math Index

34.3

176th of 269

Top 66%

Speed

60 tok/s

Top 71%

TTFT

0.57s

Market Position

Devstral Small 2Market Average