MiniMax M1 80K wins more areas, narrowly.
Scores updated · 25 tests both models report · How we compare
Where each one wins
Tests won in each of the four 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.
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.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where MiniMax M1 80K pulls ahead
- Reasons across sets of long documentsAA-LCR+2points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+1.5points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+1.1points ahead
Where MiniMax M1 40K pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 25 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingEven
- Terminal-Bench Hardtie2.33tie
- SciCodetie37.837.4tie
- SWE-bench Verifiedtie55.656tie
ReasoningMiniMax M1 80K
- GPQA DiamondMiniMax M1 80K by 1.568.269.7+1.5
- Humanity's Last ExamMiniMax M1 80K by 1.17.88.9+1.1
Long documentsMiniMax M1 80K
- AA-LCRMiniMax M1 80K by 255.757.7+2
- LongBench v2tie6161.5tie
Following instructionsEven
- IFBenchtie41.241.8tie
- Multi-Challengetie44.744.7tie
Other results16 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.
- ZebraLogicMiniMax M1 80K by 6.780.186.8+6.7
- TAU-bench (retail)MiniMax M1 40K by 4.367.863.5+4.3
- AIME 2024MiniMax M1 80K by 2.783.386+2.7
- LiveCodeBenchMiniMax M1 80K by 2.762.365+2.7
- LiveCodeBench (24/8~25/5)MiniMax M1 80K by 2.762.365+2.7
- OpenAI-MRCR (128k)MiniMax M1 40K by 2.776.173.4+2.7
- τ²-Bench Telecom (AA run)MiniMax M1 80K by 2.631.634.2+2.6
- OpenAI-MRCR (1M)MiniMax M1 40K by 2.458.656.2+2.4
- AIME 2025MiniMax M1 80K by 2.374.676.9+2.3
- TAU-bench (airline)MiniMax M1 80K by 26062+2
- AA IntelligenceMiniMax M1 80K by 1.71011.7+1.7
- MATH-500 (EM)tie9696.8tie
- FullStackBenchtie67.668.3tie
- SimpleQAtie17.918.5tie
- MMLU-Protie80.681.1tie
- Artificial Analysis Coding Indextie14.114.5tie
Questions people ask
Which is better, MiniMax M1 40K or MiniMax M1 80K?
MiniMax M1 80K wins two of the four areas where both have results: reasoning and long documents. MiniMax M1 40K wins none. They are level on coding and following instructions.
Which is better for coding?
Neither. All 3 coding tests both models report are ties.
How do you compare the two?
We use the 25 benchmark tests both models have published scores on. The verdict counts the 9 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 16 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.