Skip to main content
Meo

Mistral: Mistral Small 3.2 24B

Mistral: Mistral Small 3.2 24B is mistralai's model. On the un-leaked meo benchmark it ranks #58 of 82 with 53.6% accuracy and an Effective Value (𝕍) of 0.0007 β€” earning a correct answer for about $0.0006 in 42s each.

as of 2026-10-18

meo rank
#58
of 82
Accuracy
53.6%
overall
𝕍 index (top=100)
0.017
raw 𝕍 0.0007 Β· N=10
$ / correct
$0.0006
42s each

Per-domain accuracy

133 correct of 250 questions asked across 11 domains Β· answer rate 100% Β· macro accuracy 53.0%. Headline accuracy is micro-averaged per meo’s methodology; per-domain question counts (correct/asked) are shown so you can judge significance.

Tape machine
93%14/15
Theory of mind
67%2/3
Logic / math / CS
65%22/34
Base-rate bias
63%26/41
Watson-Glaser
50%2/4
Regex automaton
50%8/16
Perceptual illusions
49%50/102
CSP (unsatisfiable)
44%7/16
Framework bias
33%1/3
Long arithmetic
7%1/15
State tracking
0%0/1

Efficiency

Cost per correct
$0.0006
Seconds per correct
42
Tokens per correct
2,260
Correct answers
133 / 250
Total benchmark cost
$0.08
Avg tokens / item
1,202

Model details

Released
2025-06-20
Weights
Open
Context
256K
Max output
16K
Knowledge cutoff
2023-10-31
Price in
$0.07/M
Price out
$0.20/M
Modality
text+image->text
View on OpenRouter β†—Hugging Face β†—

Sources: openrouter Β· meo

FAQ

How accurate is Mistral: Mistral Small 3.2 24B?

Mistral: Mistral Small 3.2 24B scores 53.6% overall on the meo benchmark (rank #58 of 82), an un-leaked private holdout graded objective-first.

What is Mistral: Mistral Small 3.2 24B's Effective Value?

Its Effective Value (𝕍) is 0.0007 at N=10, Ο‰=1, Ξ΄=1.5 β€” a fused metric of accuracy, speed, cost, and error-cascade. 𝕍 rankings shift with task depth.

How much does Mistral: Mistral Small 3.2 24B cost per correct answer?

About $0.0006 per correct answer (2,260 tokens, 42 seconds each) at benchmark-time pricing via OpenRouter.

Is Mistral: Mistral Small 3.2 24B open weights?

Yes β€” Mistral: Mistral Small 3.2 24B is released with open weights.

Benchmark updates affecting this model

  • 2026-06-09majorlogic_math_cs ground truth was broken β€” culled and rebuilt with solver-verified items

    A 5-lab frontier jury revealed that 29 of 37 LLM-authored logic_math_cs items had broken ground truth: on most, five independent frontier models unanimously concluded the clue sets were contradictory while the stored answer claimed a number, and on eight, all five agreed on the SAME different number (author arithmetic errors). Models were being marked wrong for being right. The 29 were retired (full audit published in the repo) and the domain rebuilt with generator-as-oracle items: an embedded constraint solver PROVES each puzzle has exactly one solution (or provably none), verified by an independent exhaustive enumerator. A 3-round difficulty study found frontier models saturate consistent human-scale logic puzzles, so items use anonymous global constraints and carry a measured difficulty gradient.

  • 2026-06-08majorCorrected base_bias grading (LLM-equivalence judge fix)

    The LLM-equivalence grader uses a reasoning model whose verdict token budget was too small, so its YES/NO answer was emitted as empty and silently counted as a failure. This understated the base_bias domain to ~7% for every model when the true accuracy is ~85-90%. We raised the judge budget, excluded its reasoning tokens from the verdict, switched to verbosity-robust conclusion matching, and re-graded the whole board.

Full benchmark changelog β†’

Embed this ranking

Show Mistral: Mistral Small 3.2 24B’s meo rank on your site β€” the badge links back here.

Related: all Mistral AI models Β· Tape-machine simulation domain Β· best Effective Value Β· biggest movers Β· methodology Β· full leaderboard.