Artificial Analysis
#44of 51
Score 11.3. Best run: mistralai/mistral-small-2603.
Intelligence Index: a composite of reasoning, knowledge, maths and coding evaluations.
Mistral
Mistral Small 4 benchmarks, ranks and price
Where Artificial Analysis, LiveBench, LMArena and Berkeley BFCL place Mistral Small 4, what it costs through OpenRouter and Vercel AI Gateway, and the models either side of it on the consensus.
Read Oct 1, 2026
#67of 85
on the LLM leaderboard, with a consensus score of 32 across 3 leaderboards.
Source: Artificial Analysis, LiveBench, LMArena and Berkeley BFCL, combined by Rank.ai.
By leaderboard
Where each leaderboard places Mistral Small 4
LiveBench
Not measured by LiveBench.
Contamination-limited questions refreshed each release: reasoning, maths, coding, data analysis, language.
LMArena
#59of 79
Score 1358. Best run: mistral-small-2506.
Blind head-to-head human votes, style controlled.
Berkeley BFCL
#23of 37
Score 37.15%. Best run: Mistral-small-2506 (FC).
Function calling and tool use, single turn to multi turn and web search.
Price and context
$0.26
OpenRouter: $0.15 in, $0.60 out. Vercel AI Gateway: $0.15 in, $0.60 out Context window 262K tokens.
Nearby
The models either side of Mistral Small 4
- #64gpt-4.1-nano-2025-04-1434
- #65Qwen3.6 27B33
- #66llama-3.3-70b-instruct32
- #67Mistral Small 432
- #68gpt-oss-120b31
- #69o3 Mini High30
- #70llama-4-scout-17b-16e-instruct30
Questions about Mistral Small 4
How good is Mistral Small 4?
Mistral Small 4 ranks #67 of 85 models on the Rank.ai LLM leaderboard, with a consensus score of 32 out of 100 across 3 leaderboards.
Is Mistral Small 4 better than llama-3.3-70b-instruct?
Not on the consensus: llama-3.3-70b-instruct scores 32 to Mistral Small 4's 32. Compare them source by source below, since the leaderboards test different things.
Is Mistral Small 4 better than gpt-oss-120b?
On the consensus, yes: 32 to 31.
How much does Mistral Small 4 cost?
$0.15 per million input tokens and $0.60 per million output tokens on OpenRouter, the cheaper listing we read. Blended at three input tokens to one output, that is $0.26 per million.
Is Mistral Small 4 good for coding?
It scores 26.6 on the Artificial Analysis Coding Index, placing it #41 for coding among the models on this leaderboard.
These models recommend brands. See if they name yours.
Enter your website. In about two minutes, Rank.ai asks ChatGPT, Claude and Gemini 12 questions your customers ask and grades how often they name you.
- Your grade out of 100How often AI names you, cites your site, and how high it ranks you.
- Who gets namedEvery competitor in the answers, most named first.
- The pages AI readsThe sources behind each answer.
- Three fixesWhat to fix first, with a brief for the first article.