Kimi K2 Instruct vs Qwen3.5 35B A3B
Wins 1 of 7 areas
Facts
Wins 5 of 7 areas
Coding · Reasoning · Math · Long documents · Following instructions
Qwen3.5 35B A3B is the stronger all-rounder.Kimi K2 Instruct is better at facts.
Scores updated · 36 tests both models report · How we compare
Where each one wins
Tests won in each of the seven 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.
- CodingWriting and fixing software06Qwen3.5 35B A3B6 of 6 tests
- ReasoningHard problems that need careful thinking02Qwen3.5 35B A3B2 of 3 tests · 1 tie
- Following instructionsDoing exactly what it is asked02Qwen3.5 35B A3B2 of 2 tests
- MathCompetition and research-level math01Qwen3.5 35B A3B1 of 1 test
- Long documentsFinding answers in very long texts01Qwen3.5 35B A3B1 of 1 test
- FactsGetting facts right instead of making them up21Kimi K2 Instruct2 of 3 tests
- AgentsCarrying out multi-step tasks on its own11Even1 each
Math and long documents 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.
Qwen3.5 35B A3B costs 27% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Qwen3.5 35B A3B pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+46.9points ahead
- Olympiad math problems with short answersIMOAnswerBench+31points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+30.8points ahead
Where Kimi K2 Instruct pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+15.7points ahead
- Real work tasks from 44 professionsGDPVal+12.8points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+5.3points ahead
Every test, side by side
All 36 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.5 35B A3B
- LiveCodeBench v6Qwen3.5 35B A3B by 20.953.774.6+20.9
- SWE-bench ProQwen3.5 35B A3B by 16.927.744.6+16.9
- SWE-bench MultilingualQwen3.5 35B A3B by 1347.360.3+13
- SciCodeQwen3.5 35B A3B by 730.737.7+7
- SWE-bench VerifiedQwen3.5 35B A3B by 3.465.869.2+3.4
- Terminal-Bench HardQwen3.5 35B A3B by 323.526.5+3
AgentsEven
- BrowseCompQwen3.5 35B A3B by 46.914.161+46.9
- GDPValKimi K2 Instruct by 12.818.25.4+12.8
ReasoningQwen3.5 35B A3B
- Humanity's Last ExamQwen3.5 35B A3B by 14.66.421+14.6
- GPQA DiamondQwen3.5 35B A3B by 7.876.784.5+7.8
- CritPttie00.9tie
FactsKimi K2 Instruct
- AA-Omniscience · Non-hallucinationKimi K2 Instruct by 15.730.314.6+15.7
- Vectara HHEM hallucination ratelower is betterQwen3.5 35B A3B by 7.417.910.5+7.4
- AA-Omniscience · AccuracyKimi K2 Instruct by 5.325.420.1+5.3
Following instructionsQwen3.5 35B A3B
- IFBenchQwen3.5 35B A3B by 30.841.772.5+30.8
- Multi-ChallengeQwen3.5 35B A3B by 5.954.160+5.9
Other results18 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.
- HMMT 2025Qwen3.5 35B A3B by 50.438.889.2+50.4
- BrowseComp-ZHQwen3.5 35B A3B by 40.728.869.5+40.7
- vectara_avg_summary_lengthQwen3.5 35B A3B by 35.759.294.9+35.7
- HumanEvalKimi K2 Instruct by 26.893.366.5+26.8
- AA Agentic IndexKimi K2 Instruct by 25.937.711.8+25.9
- AA-OmniscienceKimi K2 Instruct by 21.5-26.6-48.1+21.5
- τ²-Bench Telecom (AA run)Qwen3.5 35B A3B by 15.873.489.2+15.8
- Artificial Analysis Coding IndexQwen3.5 35B A3B by 11.125.937+11.1
- GPQA (unspecified)Qwen3.5 35B A3B by 1074.284.2+10
- OJBenchQwen3.5 35B A3B by 8.927.136+8.9
- MMLUKimi K2 Instruct by 8.489.581.1+8.4
- vectara_factual_consistencyQwen3.5 35B A3B by 7.482.189.5+7.4
- SuperGPQAQwen3.5 35B A3B by 6.257.263.4+6.2
- MMLU-ProQwen3.5 35B A3B by 4.281.185.3+4.2
- AA IntelligenceQwen3.5 35B A3B by 415.319.3+4
- IFEvalQwen3.5 35B A3B by 2.189.891.9+2.1
- vectara_answer_rateQwen3.5 35B A3B by 1.298.699.8+1.2
- MMLU-Reduxtie92.793.3tie
Questions people ask
Which is better, Kimi K2 Instruct or Qwen3.5 35B A3B?
Qwen3.5 35B A3B wins five of the seven areas where both have results: coding, reasoning, math, long documents and following instructions. Kimi K2 Instruct wins facts. They are level on agents.
Which is better for coding?
Qwen3.5 35B A3B. It wins 6 of the 6 coding tests both models report; Kimi K2 Instruct wins none.
Which is cheaper?
Kimi K2 Instruct costs $0.60 per million input tokens and $2.50 per million output tokens; Qwen3.5 35B A3B costs $0.25 and $2.00. That makes Qwen3.5 35B A3B about 27% cheaper for the same work.
How do you compare the two?
We use the 36 benchmark tests both models have published scores on. The verdict counts the 18 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 18 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.