Command A+ vs GPT-4.1 mini
Wins 5 of 7 areas
Coding · Reasoning · Images and charts · Long documents · Following instructions
Wins 0 of 7 areas
—
Command A+ is the stronger all-rounder.
Scores updated · 21 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.
- Images and chartsUnderstanding pictures, charts and video31Command A+3 of 4 tests
- ReasoningHard problems that need careful thinking20Command A+2 of 3 tests · 1 tie
- CodingWriting and fixing software21Command A+2 of 3 tests
- Long documentsFinding answers in very long texts10Command A+1 of 1 test
- Following instructionsDoing exactly what it is asked10Command A+1 of 1 test
- AgentsCarrying out multi-step tasks on its own00Even0 each · 1 tie
- FactsGetting facts right instead of making them up11Even1 each
Agents, 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.
Command A+ costs 10% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Command A+ pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+78.5points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+35.6points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+17.4points ahead
Where GPT-4.1 mini pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+11.4points ahead
- Reasoning about charts from research papersCharXiv (RQ)+4.1points ahead
- Code for real scientific research problemsSciCode+1.9points ahead
Every test, side by side
All 21 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingCommand A+
- Terminal-Bench HardCommand A+ by 17.4257.6+17.4
- Terminal-Bench 2.1Command A+ by 12.722.810.1+12.7
- SciCodeGPT-4.1 mini by 1.938.540.4+1.9
ReasoningCommand A+
- GPQA DiamondCommand A+ by 9.776.166.4+9.7
- Humanity's Last ExamCommand A+ by 7125+7
- CritPttie0.30tie
FactsEven
- AA-Omniscience · Non-hallucinationCommand A+ by 78.585.87.3+78.5
- AA-Omniscience · AccuracyGPT-4.1 mini by 11.48.920.3+11.4
Images and chartsCommand A+
- MathVistaCommand A+ by 7.580.673.1+7.5
- MMMU-ProCommand A+ by 4.563.258.7+4.5
- CharXiv (RQ)GPT-4.1 mini by 4.152.756.8+4.1
- MMMUCommand A+ by 2.475.172.7+2.4
Following instructionsCommand A+
- IFBenchCommand A+ by 35.673.938.3+35.6
Other results6 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.
- AIME 2025Command A+ by 49.89040.2+49.8
- AA-OmniscienceCommand A+ by 49.6-4-53.6+49.6
- τ²-Bench Telecom (AA run)Command A+ by 27.880.752.9+27.8
- Artificial Analysis Coding IndexCommand A+ by 7.627.820.2+7.6
- AA IntelligenceCommand A+ by 2.913.110.2+2.9
- AA Agentic IndexCommand A+ by 1.83.61.8+1.8
Questions people ask
Which is better, Command A+ or GPT-4.1 mini?
Command A+ wins five of the seven areas where both have results: coding, reasoning, images and charts, long documents and following instructions. GPT-4.1 mini wins none. They are level on agents and facts.
Which is better for coding?
Command A+. It wins 2 of the 3 coding tests both models report; GPT-4.1 mini wins 1.
Which is cheaper?
Command A+ costs $0.30 per million input tokens and $1.50 per million output tokens; GPT-4.1 mini costs $0.40 and $1.60. That makes Command A+ about 10% cheaper for the same work.
How do you compare the two?
We use the 21 benchmark tests both models have published scores on. The verdict counts the 15 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 6 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.