Llama 4 Maverick vs o3
Wins 0 of 7 areas
—
Wins 7 of 7 areas
Coding · Agents · Reasoning · Facts · Images and charts · Long documents · Following instructions
o3 is the stronger all-rounder.Llama 4 Maverick is cheaper.
Scores updated · 26 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 thinking05o35 of 5 tests
- CodingWriting and fixing software03o33 of 3 tests
- Images and chartsUnderstanding pictures, charts and video03o33 of 3 tests
- FactsGetting facts right instead of making them up01o31 of 2 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own01o31 of 1 test
- Long documentsFinding answers in very long texts01o31 of 1 test
- Following instructionsDoing exactly what it is asked01o31 of 1 test
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.
Llama 4 Maverick costs 89% 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 o3 pulls ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+48.1points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+30.3points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+28.4points ahead
Where Llama 4 Maverick pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 26 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Codingo3
- SWE-bench Verifiedo3 by 48.12169.1+48.1
- Terminal-Bench Hardo3 by 30.36.837.1+30.3
- SciCodeo3 by 9.331.741+9.3
Reasoningo3
- SimpleBencho3 by 25.427.753.1+25.4
- GPQA Diamondo3 by 15.667.182.7+15.6
- Humanity's Last Examo3 by 15.24.920.1+15.2
- ARC-AGI-2o3 by 6.506.5+6.5
- CritPto3 by 1.101.1+1.1
Factso3
- AA-Omniscience · Accuracyo3 by 13.724.938.6+13.7
- AA-Omniscience · Non-hallucinationtie11.111.9tie
Images and chartso3
Other results10 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. 2025o3 by 69.28.377.5+69.2
- Aider-Polygloto3 by 65.715.681.3+65.7
- AIME 2025o3 by 63.922.586.4+63.9
- τ²-Bench Telecom (AA run)o3 by 62.917.880.7+62.9
- ARC-AGI-1o3 by 56.44.460.8+56.4
- LiveCodeBencho3 by 41.343.484.7+41.3
- AA-Omniscienceo3 by 26.3-41.9-15.6+26.3
- Artificial Analysis Coding Indexo3 by 22.116.338.4+22.1
- AA Intelligenceo3 by 10.21020.2+10.2
- MMLU-Proo3 by 4.580.585+4.5
Questions people ask
Which is better, Llama 4 Maverick or o3?
o3 wins all seven areas where both have results: coding, agents, reasoning, facts, images and charts, long documents and following instructions. Llama 4 Maverick wins none, but costs 89% less.
Which is better for coding?
o3. It wins 3 of the 3 coding tests both models report; Llama 4 Maverick wins none.
Which is cheaper?
Llama 4 Maverick costs $0.25 per million input tokens and $0.87 per million output tokens; o3 costs $2.00 and $8.00. That makes Llama 4 Maverick about 89% cheaper for the same work.
How do you compare the two?
We use the 26 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 10 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.