Kimi K2.6 vs Qwen3.8 Max Preview
Wins 0 of 8 areas
—
Wins 7 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Following instructions
Qwen3.8 Max Preview is the stronger all-rounder.Kimi K2.6 is cheaper.
Scores updated · 37 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.
- AgentsCarrying out multi-step tasks on its own06Qwen3.8 Max Preview6 of 6 tests
- ReasoningHard problems that need careful thinking04Qwen3.8 Max Preview4 of 4 tests
- CodingWriting and fixing software14Qwen3.8 Max Preview4 of 6 tests · 1 tie
- MathCompetition and research-level math03Qwen3.8 Max Preview3 of 3 tests
- FactsGetting facts right instead of making them up02Qwen3.8 Max Preview2 of 3 tests · 1 tie
- Images and chartsUnderstanding pictures, charts and video02Qwen3.8 Max Preview2 of 2 tests
- Following instructionsDoing exactly what it is asked02Qwen3.8 Max Preview2 of 2 tests
- Long documentsFinding answers in very long texts00Even0 each · 1 tie
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.
Kimi K2.6 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 Qwen3.8 Max Preview pulls ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+38.4points ahead
- Real work tasks from 44 professionsGDPVal+31.4points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+24.5points ahead
Where Kimi K2.6 pulls ahead
- Programming problems, refreshed regularlyLiveBench · Coding+5.7points ahead
Every test, side by side
All 37 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.8 Max Preview
- Terminal-Bench 2.1Qwen3.8 Max Preview by 22.965.988.8+22.9
- LiveBench · Agentic CodingQwen3.8 Max Preview by 17.846.964.7+17.8
- LMArena · WebDevQwen3.8 Max Preview by 163 rating points15091672+163 rating
- SWE-bench ProQwen3.8 Max Preview by 9.158.667.7+9.1
- LiveBench · CodingKimi K2.6 by 5.778.672.9+5.7
- SciCodetie51.552.1tie
AgentsQwen3.8 Max Preview
- Terminal-Bench 4.0Qwen3.8 Max Preview by 38.40.538.9+38.4
- GDPValQwen3.8 Max Preview by 31.426.958.3+31.4
- τ-Bench V3 · BankingQwen3.8 Max Preview by 24.523.347.8+24.5
- AA ApexAgentsQwen3.8 Max Preview by 13.928.542.4+13.9
- OSWorld-VerifiedQwen3.8 Max Preview by 1373.186.1+13
- AA IT-Bench SREQwen3.8 Max Preview by 9.131.240.3+9.1
ReasoningQwen3.8 Max Preview
- CritPtQwen3.8 Max Preview by 9.7817.7+9.7
- LiveBench · ReasoningQwen3.8 Max Preview by 8.879.488.2+8.8
- Humanity's Last ExamQwen3.8 Max Preview by 5.637.543.1+5.6
- GPQA DiamondQwen3.8 Max Preview by 1.791.192.8+1.7
FactsQwen3.8 Max Preview
- SimpleQA VerifiedQwen3.8 Max Preview by 12.434.947.3+12.4
- AA-Omniscience · Non-hallucinationQwen3.8 Max Preview by 11.759.571.2+11.7
- AA-Omniscience · Accuracytie32.631.7tie
Images and chartsQwen3.8 Max Preview
- MMMU-ProQwen3.8 Max Preview by 3.479.482.8+3.4
- LMArena · VisionQwen3.8 Max Preview by 31 rating points12831314+31 rating
MathQwen3.8 Max Preview
- FrontierMath Tier 4Qwen3.8 Max Preview by 20.725.646.3+20.7
- FrontierMath Tiers 1-3 (v2)Qwen3.8 Max Preview by 17.557.274.7+17.5
- LiveBench · MathematicsQwen3.8 Max Preview by 784.391.3+7
Following instructionsQwen3.8 Max Preview
- LiveBench · Instruction FollowingQwen3.8 Max Preview by 9.764.474.1+9.7
- IFBenchQwen3.8 Max Preview by 6.87682.8+6.8
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.
- GDPval-AA v2Qwen3.8 Max Preview by 549 rating points11901739+549 rating
- AA Agentic IndexQwen3.8 Max Preview by 27.522.149.6+27.5
- ToolathlonQwen3.8 Max Preview by 22.55072.5+22.5
- AA IntelligenceQwen3.8 Max Preview by 18.42745.4+18.4
- livebench_data_analysisQwen3.8 Max Preview by 13.365.178.4+13.3
- Artificial Analysis Coding IndexQwen3.8 Max Preview by 1061.871.8+10
- AA-OmniscienceQwen3.8 Max Preview by 6.75.312+6.7
- livebench_languageQwen3.8 Max Preview by 4.675.179.7+4.6
- HLE (with tools)Qwen3.8 Max Preview by 2.25456.2+2.2
- WideSearchQwen3.8 Max Preview by 1.180.881.9+1.1
Questions people ask
Which is better, Kimi K2.6 or Qwen3.8 Max Preview?
Qwen3.8 Max Preview wins seven of the eight areas we test: coding, agents, reasoning, facts, images and charts, math and following instructions. Kimi K2.6 wins none, but costs 38% less. They are level on long documents.
Which is better for coding?
Qwen3.8 Max Preview. It wins 4 of the 6 coding tests both models report; Kimi K2.6 wins 1, and 1 is a tie.
Which is cheaper?
Kimi K2.6 costs $0.95 per million input tokens and $4.00 per million output tokens; Qwen3.8 Max Preview costs $2.00 and $6.00. That makes Kimi K2.6 about 38% cheaper for the same work.
How do you compare the two?
We use the 37 benchmark tests both models have published scores on. The verdict counts the 27 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.