Kimi K2.6 vs Qwen3.7 Plus Preview
Wins 5 of 8 areas
Coding · Agents · Reasoning · Math · Long documents
Wins 2 of 8 areas
Images and charts · Following instructions
Kimi K2.6 is the stronger all-rounder.Qwen3.7 Plus Preview is cheaper and better at images and charts.
Scores updated · 39 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 software41Kimi K2.64 of 7 tests · 2 ties
- AgentsCarrying out multi-step tasks on its own31Kimi K2.63 of 6 tests · 2 ties
- ReasoningHard problems that need careful thinking21Kimi K2.62 of 3 tests
- MathCompetition and research-level math10Kimi K2.61 of 3 tests · 2 ties
- Long documentsFinding answers in very long texts10Kimi K2.61 of 1 test
- Images and chartsUnderstanding pictures, charts and video01Qwen3.7 Plus Preview1 of 3 tests · 2 ties
- Following instructionsDoing exactly what it is asked01Qwen3.7 Plus Preview1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
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.
Qwen3.7 Plus Preview costs 60% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Kimi K2.6 pulls ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+22.8points ahead
- Real work tasks from 44 professionsGDPVal+13.5points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+10.1points ahead
Where Qwen3.7 Plus Preview pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+12.8points ahead
- Multi-step tasks using many real software toolsMCP Atlas+5.1points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+3.1points ahead
Every test, side by side
All 39 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 5.451.546.1+5.4
- Terminal-Bench 2.1Kimi K2.6 by 4.965.961+4.9
- Terminal-Bench HardQwen3.7 Plus Preview by 3.143.947+3.1
- SWE-bench VerifiedKimi K2.6 by 2.580.277.7+2.5
- SWE-bench ProKimi K2.6 by 158.657.6+1
- SWE-bench Multilingualtie76.775.8tie
- LiveCodeBench v6tie89.689.6tie
AgentsKimi K2.6
- GDPValKimi K2.6 by 13.526.913.4+13.5
- AA ApexAgentsKimi K2.6 by 6.128.522.4+6.1
- τ-Bench V3 · BankingKimi K2.6 by 5.823.317.5+5.8
- MCP AtlasQwen3.7 Plus Preview by 5.168.173.2+5.1
- Terminal-Bench 4.0tie0.51tie
- OSWorld-Verifiedtie73.173.3tie
ReasoningKimi K2.6
- Humanity's Last ExamKimi K2.6 by 1.937.535.6+1.9
- CritPtQwen3.7 Plus Preview by 1.189.1+1.1
- GPQA DiamondKimi K2.6 by 1.191.190+1.1
FactsEven
- AA-Omniscience · Non-hallucinationQwen3.7 Plus Preview by 12.859.572.3+12.8
- AA-Omniscience · AccuracyKimi K2.6 by 10.132.622.5+10.1
Images and chartsQwen3.7 Plus Preview
- MMMU-ProQwen3.7 Plus Preview by 1.179.480.5+1.1
- CharXiv (RQ)tie86.785.9tie
- LMArena · Visiontie12821277tie
MathKimi K2.6
- FrontierMath Tiers 1-3 (v2)Kimi K2.6 by 22.857.234.4+22.8
- HMMT Feb. 2026tie92.792.9tie
- IMOAnswerBenchtie8686tie
Following instructionsQwen3.7 Plus Preview
- IFBenchQwen3.7 Plus Preview by 27678+2
Other results13 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.
- Claw Eval (pass@3)Kimi K2.6 by 18.280.962.7+18.2
- Finance Agent v2Kimi K2.6 by 6.744.938.2+6.7
- Artificial Analysis Coding IndexKimi K2.6 by 5.961.855.9+5.9
- AA-OmniscienceKimi K2.6 by 4.25.31.1+4.2
- Terminal-Bench 2.0Qwen3.7 Plus Preview by 3.666.770.3+3.6
- MATH-VisionKimi K2.6 by 2.993.290.3+2.9
- τ²-Bench Telecom (AA run)Kimi K2.6 by 2.995.993+2.9
- MCPMarkQwen3.7 Plus Preview by 2.855.958.7+2.8
- AA Agentic IndexKimi K2.6 by 2.422.119.7+2.4
- BabyVisionQwen3.7 Plus Preview by 1.968.570.4+1.9
- AA IntelligenceKimi K2.6 by 1.82725.2+1.8
- MMLU-ProQwen3.7 Plus Preview by 1.487.188.5+1.4
- Apex (Pass@1)Kimi K2.6 by 1.32422.7+1.3
Questions people ask
Which is better, Kimi K2.6 or Qwen3.7 Plus Preview?
Kimi K2.6 wins five of the eight areas we test: coding, agents, reasoning, math and long documents. Qwen3.7 Plus Preview wins images and charts and following instructions, and costs 60% less. They are level on facts.
Which is better for coding?
Kimi K2.6. It wins 4 of the 7 coding tests both models report; Qwen3.7 Plus Preview wins 1, and 2 are ties.
Which is cheaper?
Kimi K2.6 costs $0.95 per million input tokens and $4.00 per million output tokens; Qwen3.7 Plus Preview costs $0.40 and $1.60. That makes Qwen3.7 Plus Preview about 60% cheaper for the same work.
How do you compare the two?
We use the 39 benchmark tests both models have published scores on. The verdict counts the 26 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 13 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.