Kimi K2.5 vs Step 3.5 Flash
Wins 5 of 7 areas
Coding · Reasoning · Facts · Long documents · Following instructions
Wins 1 of 7 areas
Math
Kimi K2.5 is the stronger all-rounder.Step 3.5 Flash is cheaper and better at math.
Scores updated · 32 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 software31Kimi K2.53 of 4 tests
- ReasoningHard problems that need careful thinking20Kimi K2.52 of 3 tests · 1 tie
- FactsGetting facts right instead of making them up20Kimi K2.52 of 2 tests
- Long documentsFinding answers in very long texts10Kimi K2.51 of 1 test
- Following instructionsDoing exactly what it is asked10Kimi K2.51 of 1 test
- MathCompetition and research-level math01Step 3.5 Flash1 of 3 tests · 2 ties
- AgentsCarrying out multi-step tasks on its own11Even1 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.
Step 3.5 Flash costs 89% 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 K2.5 pulls ahead
- Reasons across sets of long documentsAA-LCR+28points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+20points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+11.6points ahead
Where Step 3.5 Flash pulls ahead
- Real work tasks from 44 professionsGDPVal+10.4points ahead
- Olympiad math problems with short answersIMOAnswerBench+3.6points ahead
- Recent programming contest problemsLiveCodeBench v6+1.4points ahead
Every test, side by side
All 32 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 8.64940.4+8.6
- Terminal-Bench HardKimi K2.5 by 7.534.827.3+7.5
- SWE-bench VerifiedKimi K2.5 by 2.476.874.4+2.4
- LiveCodeBench v6Step 3.5 Flash by 1.48586.4+1.4
AgentsEven
- GDPValStep 3.5 Flash by 10.417.227.6+10.4
- BrowseCompKimi K2.5 by 5.974.969+5.9
ReasoningKimi K2.5
- Humanity's Last ExamKimi K2.5 by 9.630.721.1+9.6
- GPQA DiamondKimi K2.5 by 4.887.983.1+4.8
- CritPttie3.12.5tie
FactsKimi K2.5
- AA-Omniscience · Non-hallucinationKimi K2.5 by 2034.314.3+20
- AA-Omniscience · AccuracyKimi K2.5 by 11.635.223.6+11.6
MathStep 3.5 Flash
- IMOAnswerBenchStep 3.5 Flash by 3.681.885.4+3.6
- AIME 2026tie95.896.7tie
- HMMT Feb. 2026tie87.186.4tie
Following instructionsKimi K2.5
- IFBenchKimi K2.5 by 5.670.264.6+5.6
Other results16 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.
- AA-OmniscienceKimi K2.5 by 34.5-7.3-41.8+34.5
- AA Agentic IndexStep 3.5 Flash by 30.321.752+30.3
- xbench-DeepSearchKimi K2.5 by 20.476.756.3+20.4
- Artificial Analysis Coding IndexKimi K2.5 by 15.246.831.6+15.2
- GAIA (no file)Step 3.5 Flash by 8.675.984.5+8.6
- AA IntelligenceKimi K2.5 by 6.923.516.6+6.9
- browsecomp_with_context_managerKimi K2.5 by 5.974.969+5.9
- ResearchRubricsStep 3.5 Flash by 5.859.565.3+5.8
- HMMT Nov. 2025Step 3.5 Flash by 4.889.294+4.8
- BrowseComp-ZHStep 3.5 Flash by 4.662.366.9+4.6
- HMMT Feb. 2025Step 3.5 Flash by 395.498.4+3
- τ²-BenchStep 3.5 Flash by 2.885.488.2+2.8
- MMLU-ProKimi K2.5 by 2.787.184.4+2.7
- τ²-Bench Telecom (AA run)Kimi K2.5 by 1.595.994.4+1.5
- AIME 2025Step 3.5 Flash by 1.296.197.3+1.2
- Terminal-Bench 2.0tie50.851tie
Questions people ask
Which is better, Kimi K2.5 or Step 3.5 Flash?
Kimi K2.5 wins five of the seven areas where both have results: coding, reasoning, facts, long documents and following instructions. Step 3.5 Flash wins math, and costs 89% less. They are level on agents.
Which is better for coding?
Kimi K2.5. It wins 3 of the 4 coding tests both models report; Step 3.5 Flash wins 1.
Which is cheaper?
Kimi K2.5 costs $0.60 per million input tokens and $3.00 per million output tokens; Step 3.5 Flash costs $0.10 and $0.30. That makes Step 3.5 Flash about 89% cheaper for the same work.
How do you compare the two?
We use the 32 benchmark tests both models have published scores on. The verdict counts the 16 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 16 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.