ERNIE 5.0 Thinking Preview vs GPT-4o
Wins 5 of 7 areas
Coding · Agents · Reasoning · Images and charts · Following instructions
Wins 2 of 7 areas
Facts · Long documents
ERNIE 5.0 Thinking Preview is the stronger all-rounder.GPT-4o is better at facts.
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 thinking30ERNIE 5.0 Thinking Preview3 of 3 tests
- CodingWriting and fixing software20ERNIE 5.0 Thinking Preview2 of 2 tests
- AgentsCarrying out multi-step tasks on its own10ERNIE 5.0 Thinking Preview1 of 1 test
- Images and chartsUnderstanding pictures, charts and video10ERNIE 5.0 Thinking Preview1 of 1 test
- Following instructionsDoing exactly what it is asked10ERNIE 5.0 Thinking Preview1 of 1 test
- FactsGetting facts right instead of making them up02GPT-4o2 of 2 tests
- Long documentsFinding answers in very long texts01GPT-4o1 of 1 test
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 78% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where ERNIE 5.0 Thinking Preview pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+25.1points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+16.7points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+11.5points ahead
Where GPT-4o pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+49.1points ahead
- Reasons across sets of long documentsAA-LCR+49points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+1.6points 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.
CodingERNIE 5.0 Thinking Preview
- Terminal-Bench HardERNIE 5.0 Thinking Preview by 16.7258.3+16.7
- SciCodeERNIE 5.0 Thinking Preview by 4.237.533.3+4.2
AgentsERNIE 5.0 Thinking Preview
- GDPValERNIE 5.0 Thinking Preview by 14.414.40+14.4
ReasoningERNIE 5.0 Thinking Preview
- GPQA DiamondERNIE 5.0 Thinking Preview by 25.177.752.6+25.1
- Humanity's Last ExamERNIE 5.0 Thinking Preview by 11.513.31.8+11.5
- CritPtERNIE 5.0 Thinking Preview by 1.41.40+1.4
FactsGPT-4o
- AA-Omniscience · Non-hallucinationGPT-4o by 49.11362.1+49.1
- AA-Omniscience · AccuracyGPT-4o by 1.622.123.7+1.6
Images and chartsERNIE 5.0 Thinking Preview
- MMMU-ProERNIE 5.0 Thinking Preview by 8.364.656.3+8.3
Following instructionsERNIE 5.0 Thinking Preview
- IFBenchERNIE 5.0 Thinking Preview by 5.441.436+5.4
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.
- AIME 2025ERNIE 5.0 Thinking Preview by 75.38711.7+75.3
- τ²-Bench Telecom (AA run)ERNIE 5.0 Thinking Preview by 5583.928.9+55
- SimpleQAERNIE 5.0 Thinking Preview by 36.87538.2+36.8
- AA-OmniscienceGPT-4o by 35.1-45.6-10.5+35.1
- AA Agentic IndexERNIE 5.0 Thinking Preview by 31.339.78.4+31.3
- MMLU-ProERNIE 5.0 Thinking Preview by 12.38774.7+12.3
- AA IntelligenceERNIE 5.0 Thinking Preview by 714.37.3+7
- Artificial Analysis Coding IndexERNIE 5.0 Thinking Preview by 529.224.2+5
Questions people ask
Which is better, ERNIE 5.0 Thinking Preview or GPT-4o?
ERNIE 5.0 Thinking Preview wins five of the seven areas where both have results: coding, agents, reasoning, images and charts and following instructions. GPT-4o wins facts and long documents.
Which is better for coding?
ERNIE 5.0 Thinking Preview. It wins 2 of the 2 coding tests both models report; GPT-4o wins none.
Which is cheaper?
ERNIE 5.0 Thinking Preview costs $0.89 per million input tokens and $3.58 per million output tokens; GPT-4o costs $5.00 and $15.00. That makes ERNIE 5.0 Thinking Preview about 78% 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.