Gemini 2.5 Pro vs Trinity Large Thinking
Wins 4 of 6 areas
Coding · Agents · Reasoning · Long documents
Wins 1 of 6 areas
Following instructions
Gemini 2.5 Pro is the stronger all-rounder.Trinity Large Thinking is cheaper and better at following instructions.
Scores updated · 22 tests both models report · How we compare
Where each one wins
Tests won in each of the six 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 thinking30Gemini 2.5 Pro3 of 3 tests
- CodingWriting and fixing software31Gemini 2.5 Pro3 of 4 tests
- AgentsCarrying out multi-step tasks on its own10Gemini 2.5 Pro1 of 3 tests · 2 ties
- Long documentsFinding answers in very long texts10Gemini 2.5 Pro1 of 1 test
- Following instructionsDoing exactly what it is asked01Trinity Large Thinking1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each · 1 tie
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.
Trinity Large Thinking costs 91% 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 2.5 Pro pulls ahead
- Reasons across sets of long documentsAA-LCR+31points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+16.6points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+8.4points ahead
Where Trinity Large Thinking pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+7.6points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+5points ahead
Every test, side by side
All 22 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 2.5 Pro
- Terminal-Bench 2.1Gemini 2.5 Pro by 7.928.520.6+7.9
- SciCodeGemini 2.5 Pro by 5.746.340.6+5.7
- Terminal-Bench HardGemini 2.5 Pro by 3.826.522.7+3.8
- LMArena · WebDevTrinity Large Thinking by 15 rating points12241239+15 rating
AgentsGemini 2.5 Pro
- τ-Bench V3 · BankingGemini 2.5 Pro by 3.99.75.8+3.9
- Terminal-Bench 4.0tie00.5tie
- GDPValtie00tie
ReasoningGemini 2.5 Pro
- GPQA DiamondGemini 2.5 Pro by 8.483.675.2+8.4
- Humanity's Last ExamGemini 2.5 Pro by 2.21815.8+2.2
- CritPtGemini 2.5 Pro by 1.72.60.9+1.7
FactsEven
- AA-Omniscience · AccuracyGemini 2.5 Pro by 16.63922.5+16.6
- AA-Omniscience · Non-hallucinationTrinity Large Thinking by 59.114.1+5
- Vectara HHEM hallucination ratelower is bettertie76.9tie
Following instructionsTrinity Large Thinking
- IFBenchTrinity Large Thinking by 7.648.756.3+7.6
Other results7 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.
- τ²-Bench Telecom (AA run)Trinity Large Thinking by 3654.190.1+36
- AA-OmniscienceGemini 2.5 Pro by 27.8-16.4-44.1+27.8
- Artificial Analysis Coding IndexGemini 2.5 Pro by 20.946.725.8+20.9
- AA IntelligenceGemini 2.5 Pro by 4.21510.8+4.2
- vectara_avg_summary_lengthTrinity Large Thinking by 10.9 rating points106.4117.3+10.9 rating
- vectara_answer_ratetie99.199tie
- vectara_factual_consistencytie9393.1tie
Questions people ask
Which is better, Gemini 2.5 Pro or Trinity Large Thinking?
Gemini 2.5 Pro wins four of the six areas where both have results: coding, agents, reasoning and long documents. Trinity Large Thinking wins following instructions, and costs 91% less. They are level on facts.
Which is better for coding?
Gemini 2.5 Pro. It wins 3 of the 4 coding tests both models report; Trinity Large Thinking wins 1.
Which is cheaper?
Gemini 2.5 Pro costs $1.25 per million input tokens and $10.00 per million output tokens; Trinity Large Thinking costs $0.25 and $0.80. That makes Trinity Large Thinking about 91% cheaper for the same work.
How do you compare the two?
We use the 22 benchmark tests both models have published scores on. The verdict counts the 15 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 7 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.