Kimi K3.1 Pro is the stronger all-rounder.ERNIE 5.5 Flash Preview is cheaper.
Scores updated · 7 tests both models report · How we compare
Where each one wins
Tests won in each of the one area 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.
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.
ERNIE 5.5 Flash Preview costs 58% 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
- Finds hard-to-locate facts by browsing the webBrowseComp+4.7points ahead
- Long professional tasks in banking, consulting and lawAA ApexAgents+3points ahead
Where ERNIE 5.5 Flash Preview pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 7 tests both models report. The winning score is in its model's colour; marks a score checked independently.
AgentsKimi K3.1 Pro
- BrowseCompKimi K3.1 Pro by 4.787.492.1+4.7
- AA ApexAgentsKimi K3.1 Pro by 364.267.2+3
Other results5 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 19.246.565.7+19.2
- Agents' Last ExamKimi K3.1 Pro by 14.22943.2+14.2
- Terminal-Bench-Science 0.1Kimi K3.1 Pro by 13.32134.3+13.3
- DeepSWE 1.1Kimi K3.1 Pro by 4.371.275.5+4.3
- OfficeQA Protie67.967.4tie
Questions people ask
Which is better, ERNIE 5.5 Flash Preview or Kimi K3.1 Pro?
Kimi K3.1 Pro wins the one area where both have results: agents. ERNIE 5.5 Flash Preview wins none, but costs 58% less.
Which is cheaper?
ERNIE 5.5 Flash Preview costs $1.00 per million input tokens and $4.00 per million output tokens; Kimi K3.1 Pro costs $2.00 and $10.00. That makes ERNIE 5.5 Flash Preview about 58% cheaper for the same work.
How do you compare the two?
We use the 7 benchmark tests both models have published scores on. The verdict counts the 2 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 5 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.