GPT-5.4 mini vs Mistral Medium 3.1 (Non-Reasoning)
Wins 7 of 7 areas
Coding · Agents · Reasoning · Facts · Images and charts · Long documents · Following instructions
Wins 0 of 7 areas
—
GPT-5.4 mini is the stronger all-rounder.Mistral Medium 3.1 (Non-Reasoning) is cheaper.
Scores updated · 24 tests both models report · How we compare
Where each one wins
Tests won in each of the seven areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- CodingWriting and fixing software30GPT-5.4 mini3 of 3 tests
- AgentsCarrying out multi-step tasks on its own30GPT-5.4 mini3 of 3 tests
- ReasoningHard problems that need careful thinking30GPT-5.4 mini3 of 3 tests
- Images and chartsUnderstanding pictures, charts and video20GPT-5.4 mini2 of 2 tests
- FactsGetting facts right instead of making them up21GPT-5.4 mini2 of 3 tests
- Long documentsFinding answers in very long texts10GPT-5.4 mini1 of 1 test
- Following instructionsDoing exactly what it is asked10GPT-5.4 mini1 of 1 test
Long documents and following instructions rest on a single test each.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
Mistral Medium 3.1 (Non-Reasoning) costs 54% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where GPT-5.4 mini pulls ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+45.3points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+41.7points ahead
- Reasons across sets of long documentsAA-LCR+34.3points ahead
Where Mistral Medium 3.1 (Non-Reasoning) pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+5.6points ahead
Every test, side by side
All 24 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-5.4 mini
- Terminal-Bench 2.1GPT-5.4 mini by 45.359.213.9+45.3
- Terminal-Bench HardGPT-5.4 mini by 41.752.310.6+41.7
- SciCodeGPT-5.4 mini by 19.752.132.4+19.7
AgentsGPT-5.4 mini
- GDPValGPT-5.4 mini by 25.825.80+25.8
- τ-Bench V3 · BankingGPT-5.4 mini by 17.425.68.2+17.4
- Terminal-Bench 4.0GPT-5.4 mini by 220+2
ReasoningGPT-5.4 mini
- GPQA DiamondGPT-5.4 mini by 28.787.558.8+28.7
- Humanity's Last ExamGPT-5.4 mini by 23.428.14.7+23.4
- CritPtGPT-5.4 mini by 10100+10
FactsGPT-5.4 mini
- Vectara HHEM hallucination ratelower is betterGPT-5.4 mini by 17.25.522.7+17.2
- AA-Omniscience · AccuracyGPT-5.4 mini by 16.737.520.8+16.7
- AA-Omniscience · Non-hallucinationMistral Medium 3.1 (Non-Reasoning) by 5.69.815.4+5.6
Images and chartsGPT-5.4 mini
- MMMU-ProGPT-5.4 mini by 19.173.354.2+19.1
- LMArena · VisionGPT-5.4 mini by 73 rating points12451172+73 rating
Following instructionsGPT-5.4 mini
- IFBenchGPT-5.4 mini by 33.573.339.8+33.5
Other results8 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- τ²-Bench Telecom (AA run)GPT-5.4 mini by 42.783.340.6+42.7
- Artificial Analysis Coding IndexGPT-5.4 mini by 35.656.120.5+35.6
- AA-OmniscienceGPT-5.4 mini by 27.4-18.9-46.3+27.4
- vectara_factual_consistencyGPT-5.4 mini by 17.294.577.3+17.2
- AA Agentic IndexGPT-5.4 mini by 16.619.73.1+16.6
- AA IntelligenceGPT-5.4 mini by 14.924.19.2+14.9
- vectara_avg_summary_lengthMistral Medium 3.1 (Non-Reasoning) by 88.2 rating points54.7142.9+88.2 rating
- vectara_answer_ratetie10099.7tie
Questions people ask
Which is better, GPT-5.4 mini or Mistral Medium 3.1 (Non-Reasoning)?
GPT-5.4 mini wins all seven areas where both have results: coding, agents, reasoning, facts, images and charts, long documents and following instructions. Mistral Medium 3.1 (Non-Reasoning) wins none, but costs 54% less.
Which is better for coding?
GPT-5.4 mini. It wins 3 of the 3 coding tests both models report; Mistral Medium 3.1 (Non-Reasoning) wins none.
Which is cheaper?
GPT-5.4 mini costs $0.75 per million input tokens and $4.50 per million output tokens; Mistral Medium 3.1 (Non-Reasoning) costs $0.40 and $2.00. That makes Mistral Medium 3.1 (Non-Reasoning) about 54% cheaper for the same work.
How do you compare the two?
We use the 24 benchmark tests both models have published scores on. The verdict counts the 16 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 8 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.