Gemini 2.5 Flash Lite vs GPT-4o
Wins 3 of 7 areas
Reasoning · Images and charts · Following instructions
Wins 2 of 7 areas
Coding · Facts
Gemini 2.5 Flash Lite wins more areas, narrowly.GPT-4o is better at coding.
Scores updated · 32 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 thinking20Gemini 2.5 Flash Lite2 of 3 tests · 1 tie
- Images and chartsUnderstanding pictures, charts and video10Gemini 2.5 Flash Lite1 of 2 tests · 1 tie
- Following instructionsDoing exactly what it is asked10Gemini 2.5 Flash Lite1 of 1 test
- CodingWriting and fixing software03GPT-4o3 of 3 tests
- FactsGetting facts right instead of making them up12GPT-4o2 of 3 tests
- AgentsCarrying out multi-step tasks on its own00Even0 each · 1 tie
- Long documentsFinding answers in very long texts00Even0 each · 1 tie
Agents, 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.
Gemini 2.5 Flash Lite costs 98% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Gemini 2.5 Flash Lite pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+13.9points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+9.9points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+5points ahead
Where GPT-4o pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+39.5points ahead
- Code for real scientific research problemsSciCode+14points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+5.8points ahead
Every test, side by side
All 32 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-4o
- SciCodeGPT-4o by 1419.333.3+14
- Terminal-Bench HardGPT-4o by 3.84.58.3+3.8
- SWE-bench VerifiedGPT-4o by 1.631.633.2+1.6
ReasoningGemini 2.5 Flash Lite
- GPQA DiamondGemini 2.5 Flash Lite by 9.962.552.6+9.9
- Humanity's Last ExamGemini 2.5 Flash Lite by 56.81.8+5
- CritPttie00tie
FactsGPT-4o
- AA-Omniscience · Non-hallucinationGPT-4o by 39.522.662.1+39.5
- Vectara HHEM hallucination ratelower is betterGemini 2.5 Flash Lite by 6.33.39.6+6.3
- AA-Omniscience · AccuracyGPT-4o by 5.817.923.7+5.8
Images and chartsGemini 2.5 Flash Lite
Following instructionsGemini 2.5 Flash Lite
- IFBenchGemini 2.5 Flash Lite by 13.949.936+13.9
Other results18 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 2025Gemini 2.5 Flash Lite by 38.149.811.7+38.1
- AA-OmniscienceGPT-4o by 35.1-45.6-10.5+35.1
- SimpleQAGPT-4o by 27.510.738.2+27.5
- HarmBenchGPT-4o by 15.96782.9+15.9
- Artificial Analysis Coding IndexGPT-4o by 14.79.524.2+14.7
- τ²-Bench Telecom (AA run)GPT-4o by 10.518.428.9+10.5
- vectara_avg_summary_lengthGemini 2.5 Flash Lite by 9.195.786.6+9.1
- vectara_factual_consistencyGemini 2.5 Flash Lite by 6.396.790.4+6.3
- vectara_answer_rateGemini 2.5 Flash Lite by 5.799.593.8+5.7
- LiveCodeBenchGPT-4o by 4.633.738.3+4.6
- Aider-PolyglotGPT-4o by 426.730.7+4
- AIR-Bench 2024Gemini 2.5 Flash Lite by 3.465.862.4+3.4
- AA Agentic IndexGPT-4o by 2.36.18.4+2.3
- simple_safety_testsGPT-4o by 296.598.5+2
- AA IntelligenceGemini 2.5 Flash Lite by 1.28.57.3+1.2
- XSTesttie97.897.3tie
- anthropic_red_teamtie98.799.1tie
- bbqtie94.995.1tie
Questions people ask
Which is better, Gemini 2.5 Flash Lite or GPT-4o?
Gemini 2.5 Flash Lite wins three of the seven areas where both have results: reasoning, images and charts and following instructions. GPT-4o wins coding and facts. They are level on agents and long documents.
Which is better for coding?
GPT-4o. It wins 3 of the 3 coding tests both models report; Gemini 2.5 Flash Lite wins none.
Which is cheaper?
Gemini 2.5 Flash Lite costs $0.10 per million input tokens and $0.40 per million output tokens; GPT-4o costs $5.00 and $15.00. That makes Gemini 2.5 Flash Lite about 98% cheaper for the same work.
How do you compare the two?
We use the 32 benchmark tests both models have published scores on. The verdict counts the 14 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 18 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.