DeepSeek-V4-Pro vs MiMo V2 Pro
Wins 4 of 6 areas
Coding · Reasoning · Long documents · Following instructions
Wins 1 of 6 areas
Agents
DeepSeek-V4-Pro is the stronger all-rounder.MiMo V2 Pro is better at agents.
Scores updated · 20 tests both models report · How we compare
Where each one wins
Tests won in each of the six 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 software50DeepSeek-V4-Pro5 of 5 tests
- ReasoningHard problems that need careful thinking30DeepSeek-V4-Pro3 of 3 tests
- Long documentsFinding answers in very long texts10DeepSeek-V4-Pro1 of 1 test
- Following instructionsDoing exactly what it is asked10DeepSeek-V4-Pro1 of 1 test
- AgentsCarrying out multi-step tasks on its own01MiMo V2 Pro1 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.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where DeepSeek-V4-Pro pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+16.4points ahead
- Research-level physics problemsCritPt+12.6points ahead
- Code for real scientific research problemsSciCode+8.3points ahead
Where MiMo V2 Pro pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+64.1points ahead
- Real work tasks from 44 professionsGDPVal+12.3points ahead
Every test, side by side
All 20 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingDeepSeek-V4-Pro
- SciCodeDeepSeek-V4-Pro by 8.350.842.5+8.3
- Terminal-Bench HardDeepSeek-V4-Pro by 5.346.240.9+5.3
- SWE-bench MultilingualDeepSeek-V4-Pro by 4.576.271.7+4.5
- LMArena · WebDevDeepSeek-V4-Pro by 31 rating points14641433+31 rating
- SWE-bench VerifiedDeepSeek-V4-Pro by 2.680.678+2.6
ReasoningDeepSeek-V4-Pro
- CritPtDeepSeek-V4-Pro by 12.612.90.3+12.6
- Humanity's Last ExamDeepSeek-V4-Pro by 7.137.530.4+7.1
- GPQA DiamondDeepSeek-V4-Pro by 1.888.887+1.8
FactsEven
- AA-Omniscience · Non-hallucinationMiMo V2 Pro by 64.15.970+64.1
- AA-Omniscience · AccuracyDeepSeek-V4-Pro by 16.44326.6+16.4
Following instructionsDeepSeek-V4-Pro
- IFBenchDeepSeek-V4-Pro by 7.776.568.8+7.7
Other results7 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 Pro by 35.127.762.8+35.1
- Artificial Analysis Coding IndexDeepSeek-V4-Pro by 1859.441.4+18
- AA-OmniscienceMiMo V2 Pro by 15.3-10.74.6+15.3
- Terminal-Bench 2.0DeepSeek-V4-Pro by 10.867.957.1+10.8
- PinchBenchDeepSeek-V4-Pro by 7.688.681+7.6
- AA IntelligenceDeepSeek-V4-Pro by 1.830.428.6+1.8
- τ²-Bench Telecom (AA run)DeepSeek-V4-Pro by 1.296.295+1.2
Questions people ask
Which is better, DeepSeek-V4-Pro or MiMo V2 Pro?
DeepSeek-V4-Pro wins four of the six areas where both have results: coding, reasoning, long documents and following instructions. MiMo V2 Pro wins agents. They are level on facts.
Which is better for coding?
DeepSeek-V4-Pro. It wins 5 of the 5 coding tests both models report; MiMo V2 Pro wins none.
How do you compare the two?
We use the 20 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 7 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.