LIVE INTELLIGENCE · part of the Xentir AI Index

GPT-4 Turbo (Apr 2024) vs Mistral Small 3.1 (mistral-small-2503)

Name: GPT-4 Turbo (Apr 2024) vs Mistral Small 3.1 (mistral-small-2503) — benchmark results
Creator: Epoch AI
License: https://creativecommons.org/licenses/by/4.0/

GPT-4 Turbo (Apr 2024) · OpenAI, released 2024-04-09
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 Small 3.1 (mistral-small-2503) leads on more of the 4 benchmarks where both are measured — GPT-4 Turbo (Apr 2024) on 1, Mistral Small 3.1 (mistral-small-2503) on 3. 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 — GPT-4 Turbo (Apr 2024) leads on 1, Mistral Small 3.1 (mistral-small-2503) leads on 3.

Benchmark	GPT-4 Turbo (Apr 2024)	Mistral Small 3.1 (mistral-small-2503)	Leads
Epoch Capabilities Index (ECI)	127.2	127.5	Mistral Small 3.1 (mistral-small-2503)
SWE-bench Verified	Not measured	Not measured	Not measured on both
GPQA Diamond	0.466	0.475	Mistral Small 3.1 (mistral-small-2503)
MATH Level 5	0.467	0.468	Mistral Small 3.1 (mistral-small-2503)
OTIS Mock AIME 2024-2025	0.067	0.058	GPT-4 Turbo (Apr 2024)
FrontierMath	Not measured	Not measured	Not measured on both
FrontierMath Tier 4	Not measured	Not measured	Not measured on both
SimpleQA Verified	Not measured	Not measured	Not measured on both
Chess Puzzles	0.060	Not measured	Comparison unavailable — Mistral Small 3.1 (mistral-small-2503) has no published result

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 Chess Puzzles.
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.

Reference price

Per 1M tokens	GPT-4 Turbo (Apr 2024)	Mistral Small 3.1 (mistral-small-2503)
Output	$30.00	—

List price as published by the vendor. Xentir does not verify negotiated or enterprise rates, and price is not a measure of capability — see Data Sources.

Full profiles

GPT-4 Turbo (Apr 2024) → · Mistral Small 3.1 (mistral-small-2503) → · the full AI Model Rankings table