Gemini 2.0 Flash (Non-Reasoning) vs o3
Wins 0 of 6 areas
—
Wins 5 of 6 areas
Coding · Agents · Reasoning · Long documents · Following instructions
o3 is the stronger all-rounder.
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 thinking03o33 of 3 tests
- CodingWriting and fixing software02o32 of 2 tests
- Following instructionsDoing exactly what it is asked02o32 of 2 tests
- AgentsCarrying out multi-step tasks on its own01o31 of 1 test
- Long documentsFinding answers in very long texts01o31 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 o3 pulls ahead
- Reasons across sets of long documentsAA-LCR+43.4points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+33.3points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+31.2points ahead
Where Gemini 2.0 Flash (Non-Reasoning) pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+1.9points 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.
Reasoningo3
- GPQA Diamondo3 by 20.462.382.7+20.4
- Humanity's Last Examo3 by 15.84.320.1+15.8
- CritPto3 by 1.101.1+1.1
FactsEven
- AA-Omniscience · Accuracyo3 by 15.123.538.6+15.1
- AA-Omniscience · Non-hallucinationGemini 2.0 Flash (Non-Reasoning) by 1.913.811.9+1.9
Following instructionso3
- IFBencho3 by 31.240.271.4+31.2
- Multi-Challengeo3 by 2436.460.4+24
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.
- τ²-Bench Telecom (AA run)o3 by 51.229.580.7+51.2
- HMMT Feb. 2025o3 by 41.735.877.5+41.7
- AIME 2025o3 by 33.153.386.4+33.1
- AA-Omniscienceo3 by 27-42.5-15.6+27
- HarmBencho3 by 26.272.298.4+26.2
- Artificial Analysis Coding Indexo3 by 24.813.638.4+24.8
- AA Agentic Indexo3 by 20.315.836.1+20.3
- AIR-Bench 2024o3 by 1767.584.5+17
- AA Intelligenceo3 by 11.38.920.2+11.3
- bbqo3 by 5.99297.9+5.9
- XSTesto3 by 4.692.797.3+4.6
- simple_safety_testso3 by 1.397.799+1.3
- anthropic_red_teamGemini 2.0 Flash (Non-Reasoning) by 1.199.398.3+1.1
Questions people ask
Which is better, Gemini 2.0 Flash (Non-Reasoning) or o3?
o3 wins five of the six areas where both have results: coding, agents, reasoning, long documents and following instructions. Gemini 2.0 Flash (Non-Reasoning) wins none. They are level on facts.
Which is better for coding?
o3. 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.