ERNIE 5.0 Thinking Preview vs Gemini 3 Pro
Wins 0 of 7 areas
—
Wins 6 of 7 areas
Coding · Agents · Reasoning · Images and charts · Long documents · Following instructions
Gemini 3 Pro is the stronger all-rounder.ERNIE 5.0 Thinking Preview is cheaper.
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 thinking03Gemini 3 Pro3 of 3 tests
- CodingWriting and fixing software02Gemini 3 Pro2 of 2 tests
- AgentsCarrying out multi-step tasks on its own01Gemini 3 Pro1 of 1 test
- Images and chartsUnderstanding pictures, charts and video01Gemini 3 Pro1 of 1 test
- Long documentsFinding answers in very long texts01Gemini 3 Pro1 of 1 test
- Following instructionsDoing exactly what it is asked01Gemini 3 Pro1 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 68% 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 Gemini 3 Pro pulls ahead
- Reasons across sets of long documentsAA-LCR+69points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+33.7points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+29points ahead
Where ERNIE 5.0 Thinking Preview pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+4.5points 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.
CodingGemini 3 Pro
- SciCodeGemini 3 Pro by 18.637.556.1+18.6
- Terminal-Bench HardGemini 3 Pro by 16.72541.7+16.7
ReasoningGemini 3 Pro
- Humanity's Last ExamGemini 3 Pro by 26.413.339.7+26.4
- GPQA DiamondGemini 3 Pro by 13.177.790.8+13.1
- CritPtGemini 3 Pro by 7.71.49.1+7.7
FactsEven
- AA-Omniscience · AccuracyGemini 3 Pro by 33.722.155.8+33.7
- AA-Omniscience · Non-hallucinationERNIE 5.0 Thinking Preview by 4.5138.5+4.5
Images and chartsGemini 3 Pro
- MMMU-ProGemini 3 Pro by 15.664.680.2+15.6
Following instructionsGemini 3 Pro
- IFBenchGemini 3 Pro by 2941.470.4+29
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-OmniscienceGemini 3 Pro by 60.9-45.615.3+60.9
- Artificial Analysis Coding IndexGemini 3 Pro by 17.329.246.5+17.3
- AA IntelligenceGemini 3 Pro by 13.714.328+13.7
- AIME 2025Gemini 3 Pro by 1387100+13
- AA Agentic IndexGemini 3 Pro by 12.339.752+12.3
- τ²-Bench Telecom (AA run)Gemini 3 Pro by 3.283.987.1+3.2
- MMLU-ProGemini 3 Pro by 3.18790.1+3.1
- SimpleQAERNIE 5.0 Thinking Preview by 2.97572.1+2.9
Questions people ask
Which is better, ERNIE 5.0 Thinking Preview or Gemini 3 Pro?
Gemini 3 Pro wins six of the seven areas where both have results: coding, agents, reasoning, images and charts, long documents and following instructions. ERNIE 5.0 Thinking Preview wins none, but costs 68% less. They are level on facts.
Which is better for coding?
Gemini 3 Pro. 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; Gemini 3 Pro costs $2.00 and $12.00. That makes ERNIE 5.0 Thinking Preview about 68% 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.