Gemini 2.0 Flash (Non-Reasoning) vs Gemini 2.5 Pro
Wins 1 of 6 areas
Agents
Wins 4 of 6 areas
Coding · Reasoning · Long documents · Following instructions
Gemini 2.5 Pro is the stronger all-rounder.Gemini 2.0 Flash (Non-Reasoning) is better at agents.
Scores updated · 24 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 thinking03Gemini 2.5 Pro3 of 3 tests
- CodingWriting and fixing software02Gemini 2.5 Pro2 of 2 tests
- Following instructionsDoing exactly what it is asked02Gemini 2.5 Pro2 of 2 tests
- Long documentsFinding answers in very long texts01Gemini 2.5 Pro1 of 1 test
- AgentsCarrying out multi-step tasks on its own10Gemini 2.0 Flash (Non-Reasoning)1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
Agents and long documents 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.
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+37.7points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+22.7points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+21.3points ahead
Where Gemini 2.0 Flash (Non-Reasoning) pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+4.7points ahead
Every test, side by side
All 24 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 2.5 Pro
- Terminal-Bench HardGemini 2.5 Pro by 22.73.826.5+22.7
- SciCodeGemini 2.5 Pro by 1333.346.3+13
AgentsGemini 2.0 Flash (Non-Reasoning)
- GDPValGemini 2.0 Flash (Non-Reasoning) by 3.33.30+3.3
ReasoningGemini 2.5 Pro
- GPQA DiamondGemini 2.5 Pro by 21.362.383.6+21.3
- Humanity's Last ExamGemini 2.5 Pro by 13.74.318+13.7
- CritPtGemini 2.5 Pro by 2.602.6+2.6
FactsEven
- AA-Omniscience · AccuracyGemini 2.5 Pro by 15.623.539+15.6
- AA-Omniscience · Non-hallucinationGemini 2.0 Flash (Non-Reasoning) by 4.713.89.1+4.7
Following instructionsGemini 2.5 Pro
- Multi-ChallengeGemini 2.5 Pro by 17.236.453.6+17.2
- IFBenchGemini 2.5 Pro by 8.540.248.7+8.5
Other results13 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.
- HMMT Feb. 2025Gemini 2.5 Pro by 4535.880.8+45
- Artificial Analysis Coding IndexGemini 2.5 Pro by 33.113.646.7+33.1
- AIME 2025Gemini 2.5 Pro by 29.753.383+29.7
- AA-OmniscienceGemini 2.5 Pro by 26.2-42.5-16.4+26.2
- τ²-Bench Telecom (AA run)Gemini 2.5 Pro by 24.629.554.1+24.6
- AA Agentic IndexGemini 2.0 Flash (Non-Reasoning) by 12.315.83.5+12.3
- HarmBenchGemini 2.0 Flash (Non-Reasoning) by 6.872.265.4+6.8
- AA IntelligenceGemini 2.5 Pro by 6.18.915+6.1
- AIR-Bench 2024Gemini 2.5 Pro by 6.167.573.6+6.1
- XSTestGemini 2.5 Pro by 692.798.7+6
- bbqGemini 2.5 Pro by 4.49296.4+4.4
- simple_safety_teststie97.797tie
- anthropic_red_teamtie99.399.5tie
Questions people ask
Which is better, Gemini 2.0 Flash (Non-Reasoning) or Gemini 2.5 Pro?
Gemini 2.5 Pro wins four of the six areas where both have results: coding, reasoning, long documents and following instructions. Gemini 2.0 Flash (Non-Reasoning) wins agents. They are level on facts.
Which is better for coding?
Gemini 2.5 Pro. It wins 2 of the 2 coding tests both models report; Gemini 2.0 Flash (Non-Reasoning) wins none.
How do you compare the two?
We use the 24 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 13 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.