MiMo V2.6 Pro is the stronger all-rounder.Kimi K3 is better at long documents.
Both rank among the ten best models we track in long documents.
Scores updated · 20 tests both models report · How we compare
Where each one wins
Tests won in each of the five 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.
- ReasoningHard problems that need careful thinking02MiMo V2.6 Pro2 of 2 tests
- CodingWriting and fixing software12MiMo V2.6 Pro2 of 3 tests
- AgentsCarrying out multi-step tasks on its own12MiMo V2.6 Pro2 of 3 tests
- Long documentsFinding answers in very long texts10Kimi K31 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
Long documents rests on a single test.
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.
MiMo V2.6 Pro costs 93% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where MiMo V2.6 Pro pulls ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+22.2points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+12.6points ahead
- Real work tasks from 44 professionsGDPVal+7.5points ahead
Where Kimi K3 pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+12.7points ahead
- Completes tasks by operating a computer desktopOSWorld-Verified+2.8points ahead
- Reasons across sets of long documentsAA-LCR+2.4points 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.
CodingMiMo V2.6 Pro
- Terminal-Bench 2.1MiMo V2.6 Pro by 4.98589.9+4.9
- LMArena · WebDevKimi K3 by 31 rating points16561625+31 rating
- SciCodeMiMo V2.6 Pro by 1.459.560.9+1.4
AgentsMiMo V2.6 Pro
- Terminal-Bench 4.0MiMo V2.6 Pro by 22.212.634.8+22.2
- GDPValMiMo V2.6 Pro by 7.551.759.2+7.5
- OSWorld-VerifiedKimi K3 by 2.884.882+2.8
ReasoningMiMo V2.6 Pro
- CritPtMiMo V2.6 Pro by 3.223.426.6+3.2
- Humanity's Last ExamMiMo V2.6 Pro by 2.546.949.4+2.5
FactsEven
- AA-Omniscience · AccuracyKimi K3 by 12.747.634.9+12.7
- AA-Omniscience · Non-hallucinationMiMo V2.6 Pro by 12.646.859.4+12.6
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.
- Program BenchKimi K3 by 51.377.826.5+51.3
- Terminal-Bench 4.0MiMo V2.6 Pro by 22.312.634.9+22.3
- CyberGymMiMo V2.6 Pro by 148094+14
- AA-OmniscienceKimi K3 by 11.319.78.4+11.3
- JobBenchMiMo V2.6 Pro by 9.152.962+9.1
- Agents' Last ExamMiMo V2.6 Pro by 3.328.331.6+3.3
- DeepSWE 1.1MiMo V2.6 Pro by 2.96971.9+2.9
- AA IntelligenceMiMo V2.6 Pro by 2.743.646.3+2.7
- Toolathlon Verifiedtie76.576.9tie
Questions people ask
Which is better, Kimi K3 or MiMo V2.6 Pro?
MiMo V2.6 Pro wins three of the five areas where both have results: coding, agents and reasoning. Kimi K3 wins long documents. They are level on facts.
Which is better for coding?
MiMo V2.6 Pro. It wins 2 of the 3 coding tests both models report; Kimi K3 wins 1.
Which is cheaper?
Kimi K3 costs $3.00 per million input tokens and $15.00 per million output tokens; MiMo V2.6 Pro costs $0.43 and $0.87. That makes MiMo V2.6 Pro about 93% cheaper for the same work.
How do you compare the two?
We use the 20 benchmark tests both models have published scores on. The verdict counts the 11 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.