Kimi K3 vs Qwen3.6 Plus
Wins 8 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Long documents · Following instructions
Wins 0 of 8 areas
—
Kimi K3 is the stronger all-rounder.Qwen3.6 Plus is cheaper.
Scores updated · 34 tests both models report · How we compare
Where each one wins
Tests won in each of the eight areas we test. 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 K35 of 5 tests
- AgentsCarrying out multi-step tasks on its own40Kimi K34 of 4 tests
- ReasoningHard problems that need careful thinking40Kimi K34 of 4 tests
- MathCompetition and research-level math30Kimi K33 of 4 tests · 1 tie
- Images and chartsUnderstanding pictures, charts and video20Kimi K32 of 2 tests
- FactsGetting facts right instead of making them up21Kimi K32 of 3 tests
- Long documentsFinding answers in very long texts10Kimi K31 of 1 test
- Following instructionsDoing exactly what it is asked10Kimi K31 of 1 test
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.
Qwen3.6 Plus costs 81% 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 Kimi K3 pulls ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+33.9points ahead
- Real work tasks from 44 professionsGDPVal+27points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+25.2points ahead
Where Qwen3.6 Plus pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+18.6points ahead
Every test, side by side
All 34 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingKimi K3
- Terminal-Bench 2.1Kimi K3 by 23.68561.4+23.6
- LiveBench · Agentic CodingKimi K3 by 20.862.241.4+20.8
- LMArena · WebDevKimi K3 by 194 rating points16551461+194 rating
- SciCodeKimi K3 by 18.859.540.7+18.8
- LiveBench · CodingKimi K3 by 3.381.578.2+3.3
AgentsKimi K3
- GDPValKimi K3 by 2751.724.7+27
- τ-Bench V3 · BankingKimi K3 by 25.24620.8+25.2
- OSWorld-VerifiedKimi K3 by 22.384.862.5+22.3
- MCP AtlasKimi K3 by 10.184.274.1+10.1
ReasoningKimi K3
- CritPtKimi K3 by 20.523.42.9+20.5
- Humanity's Last ExamKimi K3 by 19.146.927.8+19.1
- LiveBench · ReasoningKimi K3 by 14.990.775.8+14.9
- GPQA DiamondKimi K3 by 5.393.588.2+5.3
FactsKimi K3
- AA-Omniscience · AccuracyKimi K3 by 21.247.626.4+21.2
- AA-Omniscience · Non-hallucinationQwen3.6 Plus by 18.646.865.4+18.6
- SimpleQA VerifiedKimi K3 by 6.550.644.1+6.5
Images and chartsKimi K3
- CharXiv (RQ)Kimi K3 by 9.891.381.5+9.8
- MMMU-ProKimi K3 by 2.580.578+2.5
MathKimi K3
- FrontierMath Tiers 1-3 (v2)Kimi K3 by 33.972.238.3+33.9
- HMMT Feb. 2026Kimi K3 by 9.29787.8+9.2
- AIME 2026Kimi K3 by 1.496.795.3+1.4
- LiveBench · Mathematicstie84.483.7tie
Following instructionsKimi K3
- LiveBench · Instruction FollowingKimi K3 by 13.171.458.3+13.1
Other results10 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.
- ToolathlonKimi K3 by 33.473.239.8+33.4
- Artificial Analysis Coding IndexKimi K3 by 21.776.254.5+21.7
- AA Agentic IndexKimi K3 by 21.650.629+21.6
- NL2RepoKimi K3 by 20.15837.9+20.1
- AA-OmniscienceKimi K3 by 18.819.70.9+18.8
- AA IntelligenceKimi K3 by 16.643.627+16.6
- livebench_languageKimi K3 by 10.585.575+10.5
- MATH-VisionKimi K3 by 9.897.888+9.8
- HLE (with tools)Kimi K3 by 9.259.850.6+9.2
- livebench_data_analysisKimi K3 by 8.878.769.9+8.8
Questions people ask
Which is better, Kimi K3 or Qwen3.6 Plus?
Kimi K3 wins all eight areas we test: coding, agents, reasoning, facts, images and charts, math, long documents and following instructions. Qwen3.6 Plus wins none, but costs 81% less.
Which is better for coding?
Kimi K3. It wins 5 of the 5 coding tests both models report; Qwen3.6 Plus wins none.
Which is cheaper?
Kimi K3 costs $3.00 per million input tokens and $15.00 per million output tokens; Qwen3.6 Plus costs $0.50 and $3.00. That makes Qwen3.6 Plus about 81% cheaper for the same work.
How do you compare the two?
We use the 34 benchmark tests both models have published scores on. The verdict counts the 24 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 10 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.