ERNIE 5.5 Flash Preview is the stronger all-rounder.
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 14% 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 ERNIE 5.5 Flash Preview pulls ahead
- Long professional tasks in banking, consulting and lawAA ApexAgents+30.5points ahead
- Multi-step tasks using many real software toolsMCP Atlas+7.8points ahead
Where GLM-5.2 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.
AgentsERNIE 5.5 Flash Preview
- AA ApexAgentsERNIE 5.5 Flash Preview by 30.564.233.7+30.5
- MCP AtlasERNIE 5.5 Flash Preview by 7.884.676.8+7.8
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.
- DeepSWE 1.1ERNIE 5.5 Flash Preview by 27.271.244+27.2
- OfficeQA ProERNIE 5.5 Flash Preview by 26.567.941.4+26.5
- NL2RepoERNIE 5.5 Flash Preview by 15.964.848.9+15.9
- SpreadsheetBench 2ERNIE 5.5 Flash Preview by 8.336.428.1+8.3
- Agents' Last ExamERNIE 5.5 Flash Preview by 5.22923.8+5.2
Questions people ask
Which is better, ERNIE 5.5 Flash Preview or GLM-5.2?
ERNIE 5.5 Flash Preview wins the one area where both have results: agents. GLM-5.2 wins none.
Which is cheaper?
ERNIE 5.5 Flash Preview costs $1.00 per million input tokens and $4.00 per million output tokens; GLM-5.2 costs $1.40 and $4.40. That makes ERNIE 5.5 Flash Preview about 14% 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.