The Model Index
Up to four models

GPT-5.4 vs Mistral Small 4

On the index (GPT-4 = 100), GPT-5.4 scores 166 and Mistral Small 4 119. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to GPT-5.4
Presets
GPT-5.4
166150–182
WeightsClosed
ReleasedMar 2026
Price in / out$2.5 / $15
Context1.05M
Core tests taken7 of 9
Mistral Small 4
119100–138
WeightsOpen
ReleasedMar 2026
Price in / out$0.15 / $0.60
Context262K
Core tests taken0 of 9

GPT-5.4 leads Mistral Small 4 by 47 points, at 21× the price.

Test by testthird-party results

GPT-5.4Mistral Small 4
0%25%50%75%100%CODINGVibe Code Bench v1.1Vibe Code Bench v1.1AGENTSDTBenchDTBenchLMCALMCA
Every result as a table
TestGPT-5.4Mistral Small 4
Coding
Vibe Code Bench v1.167.4%0.0%
Agents
DTBench94.4%70.9%
LMCA52.0%20.6%
Task length · METR45 sec

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG