Gemini 3 Pro vs Llama 4 Scout
Wins 6 of 7 areas
Coding · Agents · Reasoning · Images and charts · Long documents · Following instructions
Wins 1 of 7 areas
Facts
Gemini 3 Pro is the stronger all-rounder.Llama 4 Scout is cheaper and better at facts.
Scores updated · 30 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 thinking40Gemini 3 Pro4 of 4 tests
- CodingWriting and fixing software30Gemini 3 Pro3 of 3 tests
- Images and chartsUnderstanding pictures, charts and video20Gemini 3 Pro2 of 2 tests
- AgentsCarrying out multi-step tasks on its own10Gemini 3 Pro1 of 1 test
- Long documentsFinding answers in very long texts10Gemini 3 Pro1 of 1 test
- Following instructionsDoing exactly what it is asked10Gemini 3 Pro1 of 1 test
- FactsGetting facts right instead of making them up12Llama 4 Scout2 of 3 tests
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 94% 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 Gemini 3 Pro pulls ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+67.1points ahead
- Reasons across sets of long documentsAA-LCR+48.3points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+40.6points ahead
Where Llama 4 Scout pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+12.1points ahead
Every test, side by side
All 30 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 3 Pro
- SWE-bench VerifiedGemini 3 Pro by 67.176.29.1+67.1
- Terminal-Bench HardGemini 3 Pro by 40.241.71.5+40.2
- SciCodeGemini 3 Pro by 34.856.121.3+34.8
ReasoningGemini 3 Pro
- Humanity's Last ExamGemini 3 Pro by 35.939.73.8+35.9
- GPQA DiamondGemini 3 Pro by 32.190.858.7+32.1
- ARC-AGI-2Gemini 3 Pro by 31.131.10+31.1
- CritPtGemini 3 Pro by 9.19.10+9.1
FactsLlama 4 Scout
- AA-Omniscience · AccuracyGemini 3 Pro by 40.655.815.2+40.6
- AA-Omniscience · Non-hallucinationLlama 4 Scout by 12.18.520.6+12.1
- Vectara HHEM hallucination ratelower is betterLlama 4 Scout by 5.913.67.7+5.9
Images and chartsGemini 3 Pro
Following instructionsGemini 3 Pro
- IFBenchGemini 3 Pro by 30.970.439.5+30.9
Other results15 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)Gemini 3 Pro by 71.687.115.5+71.6
- AA-OmniscienceGemini 3 Pro by 67.415.3-52.1+67.4
- LiveCodeBenchGemini 3 Pro by 59.29232.8+59.2
- Artificial Analysis Coding IndexGemini 3 Pro by 38.346.58.2+38.3
- AIR-Bench 2024Gemini 3 Pro by 20.973.252.3+20.9
- AA IntelligenceGemini 3 Pro by 19.9288.1+19.9
- MMLU-ProGemini 3 Pro by 15.890.174.3+15.8
- HarmBenchGemini 3 Pro by 12.572.560+12.5
- bbqGemini 3 Pro by 10.998.487.5+10.9
- vectara_factual_consistencyLlama 4 Scout by 5.986.492.3+5.9
- vectara_avg_summary_lengthLlama 4 Scout by 35.4 rating points101.9137.3+35.4 rating
- XSTestGemini 3 Pro by 1.797.395.6+1.7
- anthropic_red_teamtie9796.5tie
- simple_safety_teststie97.597tie
- vectara_answer_ratetie99.499tie
Questions people ask
Which is better, Gemini 3 Pro or Llama 4 Scout?
Gemini 3 Pro wins six of the seven areas where both have results: coding, agents, reasoning, images and charts, long documents and following instructions. Llama 4 Scout wins facts, and costs 94% less.
Which is better for coding?
Gemini 3 Pro. It wins 3 of the 3 coding tests both models report; Llama 4 Scout wins none.
Which is cheaper?
Gemini 3 Pro costs $2.00 per million input tokens and $12.00 per million output tokens; Llama 4 Scout costs $0.19 and $0.68. That makes Llama 4 Scout about 94% cheaper for the same work.
How do you compare the two?
We use the 30 benchmark tests both models have published scores on. The verdict counts the 15 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 15 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.