Gemini 2.5 Flash vs o4-mini
Wins 2 of 7 areas
Facts · Long documents
Wins 4 of 7 areas
Coding · Agents · Reasoning · Following instructions
o4-mini wins more areas, narrowly.Gemini 2.5 Flash is cheaper and better at facts.
Scores updated · 38 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.
- CodingWriting and fixing software03o4-mini3 of 3 tests
- ReasoningHard problems that need careful thinking02o4-mini2 of 4 tests · 2 ties
- AgentsCarrying out multi-step tasks on its own01o4-mini1 of 1 test
- Following instructionsDoing exactly what it is asked01o4-mini1 of 1 test
- FactsGetting facts right instead of making them up30Gemini 2.5 Flash3 of 3 tests
- Long documentsFinding answers in very long texts10Gemini 2.5 Flash1 of 1 test
- Images and chartsUnderstanding pictures, charts and video11Even1 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 costs 49% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where o4-mini pulls ahead
Where Gemini 2.5 Flash pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+5.2points ahead
- Reasons across sets of long documentsAA-LCR+4.3points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+1.2points ahead
Every test, side by side
All 38 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Codingo4-mini
- SciCodeo4-mini by 17.429.146.5+17.4
- SWE-bench Verifiedo4-mini by 7.760.468.1+7.7
- Terminal-Bench Hardo4-mini by 1.613.615.2+1.6
Reasoningo4-mini
- Humanity's Last Examo4-mini by 4.412.116.5+4.4
- ARC-AGI-2o4-mini by 3.62.56.1+3.6
- GPQA Diamondtie7978.4tie
- CritPttie1.10.6tie
FactsGemini 2.5 Flash
- Vectara HHEM hallucination ratelower is betterGemini 2.5 Flash by 10.87.818.6+10.8
- AA-Omniscience · Non-hallucinationGemini 2.5 Flash by 5.224.719.5+5.2
- AA-Omniscience · AccuracyGemini 2.5 Flash by 1.225.924.8+1.2
Images and chartsEven
- LMArena · VisionGemini 2.5 Flash by 41 rating points12351194+41 rating
- MMMUo4-mini by 1.979.781.6+1.9
- MMMU-Protie69.169.2tie
Other results22 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.
- HarmBencho4-mini by 34.462.697+34.4
- ARC-AGI-1o4-mini by 26.432.358.7+26.4
- τ²-Bench Telecom (AA run)o4-mini by 2431.655.6+24
- AIME 2025o4-mini by 20.77292.7+20.7
- AA Agentic Indexo4-mini by 17.318.836.1+17.3
- vectara_factual_consistencyGemini 2.5 Flash by 10.892.281.4+10.8
- AIR-Bench 2024o4-mini by 9.868.778.5+9.8
- Aider-Polygloto4-mini by 761.968.9+7
- AA-OmniscienceGemini 2.5 Flash by 5.9-29.8-35.7+5.9
- bbqGemini 2.5 Flash by 3.797.794+3.7
- livecodebench_mediumo4-mini by 3.782.586.2+3.7
- AA Intelligenceo4-mini by 3.613.116.7+3.6
- Artificial Analysis Coding Indexo4-mini by 3.422.225.6+3.4
- vectara_avg_summary_lengtho4-mini by 26.2 rating points101.5127.7+26.2 rating
- frontiermath_tier_4_v1o4-mini by 2.14.26.3+2.1
- simple_safety_testso4-mini by 298100+2
- XSTestGemini 2.5 Flash by 1.498.897.4+1.4
- LiveCodeBencho4-mini by 1.276.277.4+1.2
- anthropic_red_teamtie98.898.2tie
- livecodebench_hardtie48.348.9tie
- livecodebench_easytie99.198.8tie
- vectara_answer_ratetie9999.2tie
Questions people ask
Which is better, Gemini 2.5 Flash or o4-mini?
o4-mini wins four of the seven areas where both have results: coding, agents, reasoning and following instructions. Gemini 2.5 Flash wins facts and long documents, and costs 49% less. They are level on images and charts.
Which is better for coding?
o4-mini. It wins 3 of the 3 coding tests both models report; Gemini 2.5 Flash wins none.
Which is cheaper?
Gemini 2.5 Flash costs $0.30 per million input tokens and $2.50 per million output tokens; o4-mini costs $1.10 and $4.40. That makes Gemini 2.5 Flash about 49% cheaper for the same work.
How do you compare the two?
We use the 38 benchmark tests both models have published scores on. The verdict counts the 16 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 22 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.