LIVE INTELLIGENCE · part of the Xentir AI Index

Mistral Large 2 (Nov 2024) vs Mistral Small 3.1 (mistral-small-2503)

Name: Mistral Large 2 (Nov 2024) vs Mistral Small 3.1 (mistral-small-2503) — benchmark results
Creator: Epoch AI
License: https://creativecommons.org/licenses/by/4.0/

Mistral Large 2 (Nov 2024) OPEN WEIGHTS · Mistral AI, released 2024-11-18
Mistral Small 3.1 (mistral-small-2503) OPEN WEIGHTS · Mistral AI, released 2025-03-17

“Epoch AI, 'AI Benchmarking Hub'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks' [online resource].” · epoch.ai/benchmarks · Licensed CC BY 4.0 · data last verified 2026-09-09 · Methodology · Data Sources

Mistral Large 2 (Nov 2024) leads on more of the 4 benchmarks where both are measured — Mistral Large 2 (Nov 2024) on 4. The remaining 5 of 9 tracked benchmarks cannot be compared: 1 has a result for only one of the two models, 4 for neither. Nothing on this page is estimated to fill those in.

Head-to-head

Measured on 4 of 9 tracked benchmarks for both models — Mistral Large 2 (Nov 2024) leads on 4.

Benchmark	Mistral Large 2 (Nov 2024)	Mistral Small 3.1 (mistral-small-2503)	Leads
Epoch Capabilities Index (ECI)	128.5	127.5	Mistral Large 2 (Nov 2024)
SWE-bench Verified	Not measured	Not measured	Not measured on both
GPQA Diamond	0.513	0.475	Mistral Large 2 (Nov 2024)
MATH Level 5	0.503	0.468	Mistral Large 2 (Nov 2024)
OTIS Mock AIME 2024-2025	0.078	0.058	Mistral Large 2 (Nov 2024)
FrontierMath	0.003	Not measured	Comparison unavailable — Mistral Small 3.1 (mistral-small-2503) has no published result
FrontierMath Tier 4	Not measured	Not measured	Not measured on both
SimpleQA Verified	Not measured	Not measured	Not measured on both
Chess Puzzles	Not measured	Not measured	Not measured on both

Benchmark results measure specific tasks and should not be treated as a universal measure of model quality. A model with no row here for a benchmark has not been measured on it — that is left blank, never estimated.

What remains uncertain

Mistral Small 3.1 (mistral-small-2503) has no published result on FrontierMath.
4 tracked benchmarks have no published result for either model.

A missing result means Xentir has not found one published by the source it cites, not that the model performs badly. See Data Sources.

Full profiles

Mistral Large 2 (Nov 2024) → · Mistral Small 3.1 (mistral-small-2503) → · the full AI Model Rankings table