DeepSeek-V4.1-Flash vs Kimi K2.6
Wins 7 of 8 areas
Coding · Agents · Reasoning · Facts · Math · Long documents · Following instructions
Wins 1 of 8 areas
Images and charts
DeepSeek-V4.1-Flash is the stronger all-rounder.Kimi K2.6 is better at images and charts.
Scores updated · 35 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 software40DeepSeek-V4.1-Flash4 of 5 tests · 1 tie
- ReasoningHard problems that need careful thinking30DeepSeek-V4.1-Flash3 of 4 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own30DeepSeek-V4.1-Flash3 of 3 tests
- MathCompetition and research-level math30DeepSeek-V4.1-Flash3 of 3 tests
- FactsGetting facts right instead of making them up21DeepSeek-V4.1-Flash2 of 3 tests
- Long documentsFinding answers in very long texts10DeepSeek-V4.1-Flash1 of 1 test
- Following instructionsDoing exactly what it is asked10DeepSeek-V4.1-Flash1 of 1 test
- Images and chartsUnderstanding pictures, charts and video02Kimi K2.62 of 3 tests · 1 tie
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.
DeepSeek-V4.1-Flash costs 70% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where DeepSeek-V4.1-Flash pulls ahead
- Fixes real GitHub issues, working as an agentLiveBench · Agentic Coding+30.4points ahead
- Real work tasks from 44 professionsGDPVal+28.1points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+26.3points ahead
Where Kimi K2.6 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+56points ahead
- Reasoning about charts from research papersCharXiv (RQ)+17.7points ahead
- Harder college exam questions with imagesMMMU-Pro+2.4points ahead
Every test, side by side
All 35 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingDeepSeek-V4.1-Flash
- LiveBench · Agentic CodingDeepSeek-V4.1-Flash by 30.477.346.9+30.4
- Terminal-Bench 2.1DeepSeek-V4.1-Flash by 24.790.665.9+24.7
- LMArena · WebDevDeepSeek-V4.1-Flash by 110 rating points16191509+110 rating
- LiveBench · CodingDeepSeek-V4.1-Flash by 1.48078.6+1.4
- SciCodetie51.951.5tie
AgentsDeepSeek-V4.1-Flash
- GDPValDeepSeek-V4.1-Flash by 28.15526.9+28.1
- Terminal-Bench 4.0DeepSeek-V4.1-Flash by 26.326.80.5+26.3
- AA IT-Bench SREDeepSeek-V4.1-Flash by 15.746.931.2+15.7
ReasoningDeepSeek-V4.1-Flash
- LiveBench · ReasoningDeepSeek-V4.1-Flash by 7.386.779.4+7.3
- CritPtDeepSeek-V4.1-Flash by 6.314.38+6.3
- Humanity's Last ExamDeepSeek-V4.1-Flash by 1.739.237.5+1.7
- GPQA Diamondtie90.991.1tie
FactsDeepSeek-V4.1-Flash
- AA-Omniscience · Non-hallucinationKimi K2.6 by 563.559.5+56
- AA-Omniscience · AccuracyDeepSeek-V4.1-Flash by 13.846.432.6+13.8
- SimpleQA VerifiedDeepSeek-V4.1-Flash by 842.934.9+8
Images and chartsKimi K2.6
- CharXiv (RQ)Kimi K2.6 by 17.76986.7+17.7
- MMMU-ProKimi K2.6 by 2.47779.4+2.4
- LMArena · Visiontie12781282tie
MathDeepSeek-V4.1-Flash
- FrontierMath Tier 4DeepSeek-V4.1-Flash by 20.746.325.6+20.7
- FrontierMath Tiers 1-3 (v2)DeepSeek-V4.1-Flash by 1471.257.2+14
- LiveBench · MathematicsDeepSeek-V4.1-Flash by 993.384.3+9
Following instructionsDeepSeek-V4.1-Flash
- LiveBench · Instruction FollowingDeepSeek-V4.1-Flash by 5.67064.4+5.6
Other results12 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.
- baby_vision_with_pythonDeepSeek-V4.1-Flash by 2492.568.5+24
- BabyVisionDeepSeek-V4.1-Flash by 21.189.668.5+21.1
- livebench_data_analysisDeepSeek-V4.1-Flash by 14.279.365.1+14.2
- AA IntelligenceDeepSeek-V4.1-Flash by 12.539.527+12.5
- AA-OmniscienceKimi K2.6 by 10.6-5.35.3+10.6
- HLE (with tools)DeepSeek-V4.1-Flash by 9.963.954+9.9
- vectara_factual_consistencyDeepSeek-V4.1-Flash by 6.695.889.2+6.6
- livebench_languageDeepSeek-V4.1-Flash by 6.181.275.1+6.1
- mmmu_pro_with_pythonDeepSeek-V4.1-Flash by 2.482.580.1+2.4
- charxiv_rq_with_pythonKimi K2.6 by 1.185.686.7+1.1
- vectara_avg_summary_lengthtie108.2116.7tie
- vectara_answer_ratetie99.999.7tie
Questions people ask
Which is better, DeepSeek-V4.1-Flash or Kimi K2.6?
DeepSeek-V4.1-Flash wins seven of the eight areas we test: coding, agents, reasoning, facts, math, long documents and following instructions. Kimi K2.6 wins images and charts.
Which is better for coding?
DeepSeek-V4.1-Flash. It wins 4 of the 5 coding tests both models report; Kimi K2.6 wins none, and 1 is a tie.
Which is cheaper?
DeepSeek-V4.1-Flash costs $0.30 per million input tokens and $1.20 per million output tokens; Kimi K2.6 costs $0.95 and $4.00. That makes DeepSeek-V4.1-Flash about 70% cheaper for the same work.
How do you compare the two?
We use the 35 benchmark tests both models have published scores on. The verdict counts the 23 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 12 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.