Kimi K2.6 vs MiMo V2 Pro
Wins 4 of 6 areas
Coding · Reasoning · Long documents · Following instructions
Wins 1 of 6 areas
Agents
Kimi K2.6 is the stronger all-rounder.MiMo V2 Pro is better at agents.
Scores updated · 22 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 software50Kimi K2.65 of 5 tests
- ReasoningHard problems that need careful thinking30Kimi K2.63 of 3 tests
- Long documentsFinding answers in very long texts10Kimi K2.61 of 1 test
- Following instructionsDoing exactly what it is asked10Kimi K2.61 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 Kimi K2.6 pulls ahead
Where MiMo V2 Pro pulls ahead
- Real work tasks from 44 professionsGDPVal+18.2points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+10.5points ahead
Every test, side by side
All 22 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingKimi K2.6
- SciCodeKimi K2.6 by 951.542.5+9
- LMArena · WebDevKimi K2.6 by 76 rating points15091433+76 rating
- SWE-bench MultilingualKimi K2.6 by 576.771.7+5
- Terminal-Bench HardKimi K2.6 by 343.940.9+3
- SWE-bench VerifiedKimi K2.6 by 2.280.278+2.2
ReasoningKimi K2.6
- CritPtKimi K2.6 by 7.780.3+7.7
- Humanity's Last ExamKimi K2.6 by 7.137.530.4+7.1
- GPQA DiamondKimi K2.6 by 4.191.187+4.1
FactsEven
- AA-Omniscience · Non-hallucinationMiMo V2 Pro by 10.559.570+10.5
- AA-Omniscience · AccuracyKimi K2.6 by 632.626.6+6
Other results9 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 40.722.162.8+40.7
- Artificial Analysis Coding IndexKimi K2.6 by 20.461.841.4+20.4
- Claw Eval (pass@3)Kimi K2.6 by 19.480.961.5+19.4
- Terminal-Bench 2.0Kimi K2.6 by 9.666.757.1+9.6
- PinchBenchKimi K2.6 by 9.290.281+9.2
- DeepSearchQA (F1)MiMo V2 Pro by 3.78386.7+3.7
- AA IntelligenceMiMo V2 Pro by 1.62728.6+1.6
- τ²-Bench Telecom (AA run)tie95.995tie
- AA-Omnisciencetie5.34.6tie
Questions people ask
Which is better, Kimi K2.6 or MiMo V2 Pro?
Kimi K2.6 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?
Kimi K2.6. 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 22 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 9 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.