Kimi K2.5 vs Qwen3.6 35B A3B
Wins 7 of 8 areas
Coding · Agents · Reasoning · Images and charts · Math · Long documents · Following instructions
Wins 0 of 8 areas
—
Kimi K2.5 is the stronger all-rounder.Qwen3.6 35B A3B is cheaper.
Scores updated · 46 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 K2.55 of 7 tests · 2 ties
- ReasoningHard problems that need careful thinking30Kimi K2.53 of 3 tests
- MathCompetition and research-level math30Kimi K2.53 of 3 tests
- AgentsCarrying out multi-step tasks on its own31Kimi K2.53 of 4 tests
- Images and chartsUnderstanding pictures, charts and video10Kimi K2.51 of 3 tests · 2 ties
- Long documentsFinding answers in very long texts10Kimi K2.51 of 1 test
- Following instructionsDoing exactly what it is asked10Kimi K2.51 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.
Qwen3.6 35B A3B costs 27% 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 K2.5 pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+26.2points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+16.4points ahead
- Code for real scientific research problemsSciCode+12.4points ahead
Where Qwen3.6 35B A3B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+15.2points ahead
- Real work tasks from 44 professionsGDPVal+2.6points ahead
Every test, side by side
All 46 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingKimi K2.5
- SciCodeKimi K2.5 by 12.44936.6+12.4
- SWE-bench MultilingualKimi K2.5 by 5.87367.2+5.8
- LiveCodeBench v6Kimi K2.5 by 4.68580.4+4.6
- SWE-bench VerifiedKimi K2.5 by 3.476.873.4+3.4
- SWE-bench ProKimi K2.5 by 1.250.749.5+1.2
- Terminal-Bench 2.1tie45.744.9tie
- Terminal-Bench Hardtie34.834.8tie
AgentsKimi K2.5
- BrowseCompKimi K2.5 by 26.274.948.7+26.2
- τ-Bench V3 · BankingKimi K2.5 by 4.914.29.3+4.9
- GDPValQwen3.6 35B A3B by 2.617.219.8+2.6
- MCP AtlasKimi K2.5 by 163.862.8+1
ReasoningKimi K2.5
- Humanity's Last ExamKimi K2.5 by 8.530.722.2+8.5
- GPQA DiamondKimi K2.5 by 3.887.984.1+3.8
- CritPtKimi K2.5 by 2.83.10.3+2.8
FactsEven
- AA-Omniscience · AccuracyKimi K2.5 by 16.435.218.8+16.4
- AA-Omniscience · Non-hallucinationQwen3.6 35B A3B by 15.234.349.5+15.2
Images and chartsKimi K2.5
- MathVistaKimi K2.5 by 3.790.186.4+3.7
- CharXiv (RQ)tie77.578tie
- MMMU-Protie75.475tie
MathKimi K2.5
- HMMT Feb. 2026Kimi K2.5 by 3.587.183.6+3.5
- AIME 2026Kimi K2.5 by 3.195.892.7+3.1
- IMOAnswerBenchKimi K2.5 by 2.981.878.9+2.9
Following instructionsKimi K2.5
- IFBenchKimi K2.5 by 5.870.264.4+5.8
Other results22 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.
- WideSearchKimi K2.5 by 18.97960.1+18.9
- AA-OmniscienceKimi K2.5 by 14.9-7.3-22.2+14.9
- SimpleVQAKimi K2.5 by 12.371.258.9+12.3
- MCPMarkQwen3.6 35B A3B by 7.529.537+7.5
- AA Agentic IndexKimi K2.5 by 6.721.715+6.7
- HMMT 2025Kimi K2.5 by 6.395.489.1+6.3
- AA IntelligenceKimi K2.5 by 5.323.518.2+5.3
- Artificial Analysis Coding IndexKimi K2.5 by 4.946.841.9+4.9
- HMMT Feb. 2025Kimi K2.5 by 4.795.490.7+4.7
- LVBenchKimi K2.5 by 4.575.971.4+4.5
- τ³-Bench BankingKimi K2.5 by 3.714.210.5+3.7
- VideoMMMUKimi K2.5 by 2.986.683.7+2.9
- NL2RepoKimi K2.5 by 2.63229.4+2.6
- MMLU-ProKimi K2.5 by 1.987.185.2+1.9
- τ³-BenchQwen3.6 35B A3B by 1.26667.2+1.2
- OmniDocBench 1.5Qwen3.6 35B A3B by 1.188.889.9+1.1
- Tool-Decathlontie27.826.9tie
- Toolathlontie27.826.9tie
- Terminal-Bench 2.0tie50.851.5tie
- GDPval-AA v2tie10091015tie
- τ²-Bench Telecom (AA run)tie95.995.3tie
- HMMT Nov. 2025tie89.289.1tie
Questions people ask
Which is better, Kimi K2.5 or Qwen3.6 35B A3B?
Kimi K2.5 wins seven of the eight areas we test: coding, agents, reasoning, images and charts, math, long documents and following instructions. Qwen3.6 35B A3B wins none, but costs 27% less. They are level on facts.
Which is better for coding?
Kimi K2.5. It wins 5 of the 7 coding tests both models report; Qwen3.6 35B A3B wins none, and 2 are ties.
Which is cheaper?
Kimi K2.5 costs $0.60 per million input tokens and $3.00 per million output tokens; Qwen3.6 35B A3B costs $0.38 and $2.25. That makes Qwen3.6 35B A3B about 27% cheaper for the same work.
How do you compare the two?
We use the 46 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 22 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.