MiMo V2 Omni vs MiniMax M3
Wins 1 of 7 areas
Agents
Wins 5 of 7 areas
Coding · Reasoning · Images and charts · Long documents · Following instructions
MiniMax M3 is the stronger all-rounder.MiMo V2 Omni is better at agents.
Scores updated · 19 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 software03MiniMax M33 of 3 tests
- ReasoningHard problems that need careful thinking03MiniMax M33 of 3 tests
- Images and chartsUnderstanding pictures, charts and video02MiniMax M32 of 2 tests
- Long documentsFinding answers in very long texts01MiniMax M31 of 1 test
- Following instructionsDoing exactly what it is asked01MiniMax M31 of 1 test
- AgentsCarrying out multi-step tasks on its own10MiMo V2 Omni1 of 1 test
- 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.
MiniMax M3 costs 38% 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 MiniMax M3 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+30.5points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+29.4points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+16.9points ahead
Where MiMo V2 Omni pulls ahead
- Real work tasks from 44 professionsGDPVal+3.8points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+2.6points ahead
Every test, side by side
All 19 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingMiniMax M3
- SciCodeMiniMax M3 by 10.436.747.1+10.4
- Terminal-Bench HardMiniMax M3 by 7.634.842.4+7.6
- SWE-bench VerifiedMiniMax M3 by 5.774.880.5+5.7
ReasoningMiniMax M3
- Humanity's Last ExamMiniMax M3 by 16.922.139+16.9
- GPQA DiamondMiniMax M3 by 10.182.892.9+10.1
- CritPtMiniMax M3 by 2.61.13.7+2.6
FactsEven
- AA-Omniscience · Non-hallucinationMiniMax M3 by 30.551.181.6+30.5
- AA-Omniscience · AccuracyMiMo V2 Omni by 2.619.316.7+2.6
Images and chartsMiniMax M3
- MMMU-ProMiniMax M3 by 8.769.978.6+8.7
- LMArena · VisionMiniMax M3 by 26 rating points12281254+26 rating
Following instructionsMiniMax M3
- IFBenchMiniMax M3 by 29.453.582.9+29.4
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.
- AA Agentic IndexMiMo V2 Omni by 27.858.630.8+27.8
- Artificial Analysis Coding IndexMiniMax M3 by 23.135.558.6+23.1
- AA-OmniscienceMiniMax M3 by 21.5-20.11.4+21.5
- Claw Eval (pass@3)MiniMax M3 by 19.754.874.5+19.7
- AA IntelligenceMiniMax M3 by 5.323.929.2+5.3
- τ²-Bench Telecom (AA run)MiMo V2 Omni by 2.391.288.9+2.3
Questions people ask
Which is better, MiMo V2 Omni or MiniMax M3?
MiniMax M3 wins five of the seven areas where both have results: coding, reasoning, images and charts, long documents and following instructions. MiMo V2 Omni wins agents. They are level on facts.
Which is better for coding?
MiniMax M3. It wins 3 of the 3 coding tests both models report; MiMo V2 Omni wins none.
Which is cheaper?
MiMo V2 Omni costs $0.40 per million input tokens and $2.00 per million output tokens; MiniMax M3 costs $0.30 and $1.20. That makes MiniMax M3 about 38% cheaper for the same work.
How do you compare the two?
We use the 19 benchmark tests both models have published scores on. The verdict counts the 13 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.