DeepSeek-V4.1-Flash vs Kimi K3.1 Pro
Wins 0 of 3 areas
—
Wins 3 of 3 areas
Coding · Reasoning · Images and charts
Kimi K3.1 Pro is the stronger all-rounder.DeepSeek-V4.1-Flash is cheaper.
Scores updated · 23 tests both models report · How we compare
Where each one wins
Tests won in each of the three 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.
Coding rests on a single test.
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 88% 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 K3.1 Pro pulls ahead
- Reasoning about charts from research papersCharXiv (RQ)+20points ahead
- Harder college exam questions with imagesMMMU-Pro+13points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+11.9points ahead
Where DeepSeek-V4.1-Flash pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 23 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingKimi K3.1 Pro
- LMArena · WebDevKimi K3.1 Pro by 76 rating points16191695+76 rating
ReasoningKimi K3.1 Pro
- Humanity's Last ExamKimi K3.1 Pro by 11.939.251.1+11.9
- GPQA DiamondKimi K3.1 Pro by 3.390.994.2+3.3
Images and chartsKimi K3.1 Pro
- CharXiv (RQ)Kimi K3.1 Pro by 206989+20
- MMMU-ProKimi K3.1 Pro by 137790+13
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.
- Terminal-Bench 4.0Kimi K3.1 Pro by 34.531.265.7+34.5
- BenchCAD w/o toolsKimi K3.1 Pro by 31.641.272.8+31.6
- Terminal-Bench-Science 0.1Kimi K3.1 Pro by 22.415.738.1+22.4
- ZeroBench_main w/ python (pass@5)Kimi K3.1 Pro by 125163+12
- SWE Marathon v1.1Kimi K3.1 Pro by 11.74051.7+11.7
- Agents' Last ExamKimi K3.1 Pro by 11.431.843.2+11.4
- Program BenchKimi K3.1 Pro by 11.220.331.5+11.2
- BenchCAD w/ toolsKimi K3.1 Pro by 11.181.692.7+11.1
- ZeroBenchDeepSeek-V4.1-Flash by 104939+10
- charxiv_rq_with_pythonKimi K3.1 Pro by 7.885.693.4+7.8
- mmmu_pro_with_pythonKimi K3.1 Pro by 7.582.590+7.5
- ChartoGraphy w/ pythonKimi K3.1 Pro by 7.28390.2+7.2
- AA IntelligenceKimi K3.1 Pro by 6.539.546+6.5
- HLE (with tools)Kimi K3.1 Pro by 6.163.970+6.1
- PostTrain Bench v1.2Kimi K3.1 Pro by 630.536.5+6
- BabyVisionKimi K3.1 Pro by 5.889.695.4+5.8
- baby_vision_with_pythonKimi K3.1 Pro by 2.992.595.4+2.9
- DeepSWE 1.1Kimi K3.1 Pro by 1.374.275.5+1.3
Questions people ask
Which is better, DeepSeek-V4.1-Flash or Kimi K3.1 Pro?
Kimi K3.1 Pro wins all three areas where both have results: coding, reasoning and images and charts. DeepSeek-V4.1-Flash wins none, but costs 88% less.
Which is better for coding?
Kimi K3.1 Pro. It wins the one coding test both models report.
Which is cheaper?
DeepSeek-V4.1-Flash costs $0.30 per million input tokens and $1.20 per million output tokens; Kimi K3.1 Pro costs $2.00 and $10.00. That makes DeepSeek-V4.1-Flash about 88% cheaper for the same work.
How do you compare the two?
We use the 23 benchmark tests both models have published scores on. The verdict counts the 5 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.