GPT-5.6 Sol vs Kimi K3.1 Pro
Wins 0 of 4 areas
—
Wins 4 of 4 areas
Coding · Agents · Reasoning · Images and charts
Kimi K3.1 Pro is the stronger all-rounder.
Scores updated · 21 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.
- AgentsCarrying out multi-step tasks on its own02Kimi K3.1 Pro2 of 2 tests
- Images and chartsUnderstanding pictures, charts and video02Kimi K3.1 Pro2 of 2 tests
- ReasoningHard problems that need careful thinking01Kimi K3.1 Pro1 of 2 tests · 1 tie
- CodingWriting and fixing software01Kimi K3.1 Pro1 of 1 test
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 50% 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+27.3points ahead
- Harder college exam questions with imagesMMMU-Pro+6.6points ahead
- Reasoning about charts from research papersCharXiv (RQ)+3.2points ahead
Where GPT-5.6 Sol pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 21 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 79 rating points16161695+79 rating
AgentsKimi K3.1 Pro
- AA ApexAgentsKimi K3.1 Pro by 27.339.967.2+27.3
- BrowseCompKimi K3.1 Pro by 1.790.492.1+1.7
ReasoningKimi K3.1 Pro
- Humanity's Last ExamKimi K3.1 Pro by 1.649.551.1+1.6
- GPQA Diamondtie94.194.2tie
Images and chartsKimi K3.1 Pro
- MMMU-ProKimi K3.1 Pro by 6.683.490+6.6
- CharXiv (RQ)Kimi K3.1 Pro by 3.285.889+3.2
Other results14 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 28.437.365.7+28.4
- Terminal-Bench-Science 0.1Kimi K3.1 Pro by 15.722.438.1+15.7
- Agents' Last ExamGPT-5.6 Sol by 9.552.743.2+9.5
- SWE-MarathonKimi K3.1 Pro by 9.242.551.7+9.2
- Program BenchKimi K3.1 Pro by 8.52331.5+8.5
- BabyVisionKimi K3.1 Pro by 6.588.995.4+6.5
- charxiv_rq_with_pythonKimi K3.1 Pro by 5.687.893.4+5.6
- HLE (with tools)Kimi K3.1 Pro by 5.564.570+5.5
- OfficeQA ProKimi K3.1 Pro by 4.263.267.4+4.2
- GDP (Surge AI)Kimi K3.1 Pro by 3.930.734.6+3.9
- DeepSWEKimi K3.1 Pro by 2.872.775.5+2.8
- DeepSWE 1.1Kimi K3.1 Pro by 2.57375.5+2.5
- AA IntelligenceGPT-5.6 Sol by 14746+1
- PostTrainBenchtie36.236.5tie
Questions people ask
Which is better, GPT-5.6 Sol or Kimi K3.1 Pro?
Kimi K3.1 Pro wins all four areas where both have results: coding, agents, reasoning and images and charts. GPT-5.6 Sol wins none.
Which is better for coding?
Kimi K3.1 Pro. It wins the one coding test both models report.
Which is cheaper?
GPT-5.6 Sol costs $4.00 per million input tokens and $20.00 per million output tokens; Kimi K3.1 Pro costs $2.00 and $10.00. That makes Kimi K3.1 Pro about 50% cheaper for the same work.
How do you compare the two?
We use the 21 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 14 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.