Kimi K3.1 Pro is the stronger all-rounder.
Scores updated · 19 tests both models report · How we compare
Where each one wins
Tests won in each of the four 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.
Kimi K3.1 Pro costs 33% 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
- Long professional tasks in banking, consulting and lawAA ApexAgents+25.9points ahead
- Harder college exam questions with imagesMMMU-Pro+9.5points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+4.2points ahead
Where Kimi K3 pulls ahead
- Reasoning about charts from research papersCharXiv (RQ)+2.3points ahead
Every test, side by side
All 19 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 39 rating points16561695+39 rating
AgentsKimi K3.1 Pro
- AA ApexAgentsKimi K3.1 Pro by 25.941.367.2+25.9
- BrowseComptie91.292.1tie
ReasoningKimi K3.1 Pro
- Humanity's Last ExamKimi K3.1 Pro by 4.246.951.1+4.2
- GPQA Diamondtie93.594.2tie
Images and chartsEven
- MMMU-ProKimi K3.1 Pro by 9.580.590+9.5
- CharXiv (RQ)Kimi K3 by 2.391.389+2.3
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.
- Terminal-Bench 4.0Kimi K3.1 Pro by 53.112.665.7+53.1
- Program BenchKimi K3 by 46.377.831.5+46.3
- Agents' Last ExamKimi K3.1 Pro by 14.928.343.2+14.9
- HLE (with tools)Kimi K3.1 Pro by 10.259.870+10.2
- BabyVisionKimi K3.1 Pro by 9.785.795.4+9.7
- SWE-MarathonKimi K3.1 Pro by 9.74251.7+9.7
- DeepSWEKimi K3.1 Pro by 867.575.5+8
- DeepSWE 1.1Kimi K3.1 Pro by 6.56975.5+6.5
- OfficeQA ProKimi K3.1 Pro by 4.163.367.4+4.1
- AA IntelligenceKimi K3.1 Pro by 2.443.646+2.4
- ZeroBenchKimi K3 by 24139+2
- PostTrainBenchtie36.636.5tie
Questions people ask
Which is better, Kimi K3 or Kimi K3.1 Pro?
Kimi K3.1 Pro wins three of the four areas where both have results: coding, agents and reasoning. Kimi K3 wins none. They are level on images and charts.
Which is better for coding?
Kimi K3.1 Pro. It wins the one coding test both models report.
Which is cheaper?
Kimi K3 costs $3.00 per million input tokens and $15.00 per million output tokens; Kimi K3.1 Pro costs $2.00 and $10.00. That makes Kimi K3.1 Pro about 33% cheaper for the same work.
How do you compare the two?
We use the 19 benchmark tests both models have published scores on. The verdict counts the 7 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.