mistral-small-3.1-2503: benchmark results

Provider: Mistral.

Aggregate Rating 1485 ± 46, rank #2551 of 10556 rated models, from 53 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Misguided Attention - riddle_two_banks_money0.5Mean native expected-behavior score (0–1)87.5
Misguided Attention - dead_schrodingers_cat1Mean native expected-behavior score (0–1)83
Misguided Attention - new_years_monty_hall0.33Mean native expected-behavior score (0–1)81.2
Misguided Attention - knights_knaves_easy1Mean native expected-behavior score (0–1)77.7
Misguided Attention - trolley_easy_forced1Mean native expected-behavior score (0–1)76.8
Misguided Attention - conjunction_fallacy_impossible0.33Mean native expected-behavior score (0–1)65.2
Misguided Attention - riddle_i_never_shave1Mean native expected-behavior score (0–1)64.3
Misguided Attention - river_crossing_even_simpler1Mean native expected-behavior score (0–1)58.9
Misguided Attention - poisoned_hot0.67Mean native expected-behavior score (0–1)57.1
Misguided Attention - jugs_1_liter1Mean native expected-behavior score (0–1)51.8
Misguided Attention - feathers_or_steel1Mean native expected-behavior score (0–1)50.9
Misguided Attention - unstoppable_force_var11Mean native expected-behavior score (0–1)50.9

Interactive version: theaggregate.ai/model?slug=mistral-small-3-1-2503 · How It Works · Data refreshed daily, snapshot 2026-11-17.