GPT-4o vs Llama 4 Scout
Wins 4 of 7 areas
Coding · Facts · Images and charts · Long documents
Wins 2 of 7 areas
Reasoning · Following instructions
GPT-4o wins more areas, narrowly.Llama 4 Scout is cheaper and better at reasoning.
Scores updated · 34 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 software30GPT-4o3 of 3 tests
- FactsGetting facts right instead of making them up21GPT-4o2 of 3 tests
- Images and chartsUnderstanding pictures, charts and video21GPT-4o2 of 3 tests
- Long documentsFinding answers in very long texts10GPT-4o1 of 1 test
- ReasoningHard problems that need careful thinking02Llama 4 Scout2 of 4 tests · 2 ties
- Following instructionsDoing exactly what it is asked01Llama 4 Scout1 of 1 test
- AgentsCarrying out multi-step tasks on its own00Even0 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.
Llama 4 Scout costs 96% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where GPT-4o pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+41.5points ahead
- Reasons across sets of long documentsAA-LCR+28.3points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+24.1points ahead
Where Llama 4 Scout pulls ahead
- Math problems shown in pictures and chartsMathVista+9.3points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+6.1points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+3.5points ahead
Every test, side by side
All 34 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-4o
- SWE-bench VerifiedGPT-4o by 24.133.29.1+24.1
- SciCodeGPT-4o by 1233.321.3+12
- Terminal-Bench HardGPT-4o by 6.88.31.5+6.8
ReasoningLlama 4 Scout
- GPQA DiamondLlama 4 Scout by 6.152.658.7+6.1
- Humanity's Last ExamLlama 4 Scout by 21.83.8+2
- ARC-AGI-2tie00tie
- CritPttie00tie
FactsGPT-4o
- AA-Omniscience · Non-hallucinationGPT-4o by 41.562.120.6+41.5
- AA-Omniscience · AccuracyGPT-4o by 8.523.715.2+8.5
- Vectara HHEM hallucination ratelower is betterLlama 4 Scout by 1.99.67.7+1.9
Images and chartsGPT-4o
Following instructionsLlama 4 Scout
- IFBenchLlama 4 Scout by 3.53639.5+3.5
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.
- AA-OmniscienceGPT-4o by 41.6-10.5-52.1+41.6
- HarmBenchGPT-4o by 22.982.960+22.9
- Artificial Analysis Coding IndexGPT-4o by 1624.28.2+16
- τ²-Bench Telecom (AA run)GPT-4o by 13.428.915.5+13.4
- AIR-Bench 2024GPT-4o by 10.162.452.3+10.1
- bbqGPT-4o by 7.695.187.5+7.6
- LiveCodeBenchGPT-4o by 5.538.332.8+5.5
- vectara_answer_rateLlama 4 Scout by 5.293.899+5.2
- vectara_avg_summary_lengthLlama 4 Scout by 50.7 rating points86.6137.3+50.7 rating
- ChartQALlama 4 Scout by 3.185.788.8+3.1
- anthropic_red_teamGPT-4o by 2.699.196.5+2.6
- vectara_factual_consistencyLlama 4 Scout by 1.990.492.3+1.9
- XSTestGPT-4o by 1.797.395.6+1.7
- DocVQALlama 4 Scout by 1.692.894.4+1.6
- simple_safety_testsGPT-4o by 1.598.597+1.5
- AA Intelligencetie7.38.1tie
- MMLU-Protie74.774.3tie
- MGSMtie90.590.6tie
Questions people ask
Which is better, GPT-4o or Llama 4 Scout?
GPT-4o wins four of the seven areas where both have results: coding, facts, images and charts and long documents. Llama 4 Scout wins reasoning and following instructions, and costs 96% less. They are level on agents.
Which is better for coding?
GPT-4o. It wins 3 of the 3 coding tests both models report; Llama 4 Scout wins none.
Which is cheaper?
GPT-4o costs $5.00 per million input tokens and $15.00 per million output tokens; Llama 4 Scout costs $0.19 and $0.68. That makes Llama 4 Scout about 96% cheaper for the same work.
How do you compare the two?
We use the 34 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 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.