ERNIE 5.0 Thinking Preview vs o3
Wins 1 of 7 areas
Agents
Wins 5 of 7 areas
Coding · Reasoning · Images and charts · Long documents · Following instructions
o3 is the stronger all-rounder.ERNIE 5.0 Thinking Preview is cheaper and better at agents.
Scores updated · 19 tests both models report · How we compare
Where each one wins
Tests won in each of the seven 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.
- ReasoningHard problems that need careful thinking02o32 of 3 tests · 1 tie
- CodingWriting and fixing software02o32 of 2 tests
- Images and chartsUnderstanding pictures, charts and video01o31 of 1 test
- Long documentsFinding answers in very long texts01o31 of 1 test
- Following instructionsDoing exactly what it is asked01o31 of 1 test
- AgentsCarrying out multi-step tasks on its own10ERNIE 5.0 Thinking Preview1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
Agents, images and charts, long documents and following instructions rest on a single test each.
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 5.0 Thinking Preview costs 55% 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 o3 pulls ahead
- Reasons across sets of long documentsAA-LCR+67.7points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+30points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+16.5points ahead
Where ERNIE 5.0 Thinking Preview pulls ahead
- Real work tasks from 44 professionsGDPVal+1.6points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+1.1points 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.
AgentsERNIE 5.0 Thinking Preview
- GDPValERNIE 5.0 Thinking Preview by 1.614.412.8+1.6
Reasoningo3
- Humanity's Last Examo3 by 6.813.320.1+6.8
- GPQA Diamondo3 by 577.782.7+5
- CritPttie1.41.1tie
FactsEven
- AA-Omniscience · Accuracyo3 by 16.522.138.6+16.5
- AA-Omniscience · Non-hallucinationERNIE 5.0 Thinking Preview by 1.11311.9+1.1
Other results8 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.
- AA-Omniscienceo3 by 30.1-45.6-15.6+30.1
- SimpleQAERNIE 5.0 Thinking Preview by 25.67549.4+25.6
- Artificial Analysis Coding Indexo3 by 9.229.238.4+9.2
- AA Intelligenceo3 by 5.914.320.2+5.9
- AA Agentic IndexERNIE 5.0 Thinking Preview by 3.639.736.1+3.6
- τ²-Bench Telecom (AA run)ERNIE 5.0 Thinking Preview by 3.283.980.7+3.2
- MMLU-ProERNIE 5.0 Thinking Preview by 28785+2
- AIME 2025tie8786.4tie
Questions people ask
Which is better, ERNIE 5.0 Thinking Preview or o3?
o3 wins five of the seven areas where both have results: coding, reasoning, images and charts, long documents and following instructions. ERNIE 5.0 Thinking Preview wins agents, and costs 55% less. They are level on facts.
Which is better for coding?
o3. It wins 2 of the 2 coding tests both models report; ERNIE 5.0 Thinking Preview wins none.
Which is cheaper?
ERNIE 5.0 Thinking Preview costs $0.89 per million input tokens and $3.58 per million output tokens; o3 costs $2.00 and $8.00. That makes ERNIE 5.0 Thinking Preview about 55% 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 11 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 8 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.