GPT-5.2 vs Llama 3.1 Instruct 405B
Wins 5 of 6 areas
Coding · Agents · Reasoning · Long documents · Following instructions
Wins 0 of 6 areas
—
GPT-5.2 is the stronger all-rounder.
Scores updated · 22 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.
- CodingWriting and fixing software40GPT-5.24 of 4 tests
- ReasoningHard problems that need careful thinking40GPT-5.24 of 4 tests
- Long documentsFinding answers in very long texts20GPT-5.22 of 2 tests
- AgentsCarrying out multi-step tasks on its own10GPT-5.21 of 1 test
- Following instructionsDoing exactly what it is asked10GPT-5.21 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
Agents 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.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where GPT-5.2 pulls ahead
- Reasons across sets of long documentsAA-LCR+57.4points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+55.5points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+40.2points ahead
Where Llama 3.1 Instruct 405B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+28.8points ahead
Every test, side by side
All 22 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-5.2
- SWE-bench VerifiedGPT-5.2 by 55.58024.5+55.5
- Terminal-Bench HardGPT-5.2 by 40.2476.8+40.2
- SciCodeGPT-5.2 by 22.252.129.9+22.2
- SWE-bench ProGPT-5.2 by 18.729.911.2+18.7
ReasoningGPT-5.2
- GPQA DiamondGPT-5.2 by 38.890.351.5+38.8
- Humanity's Last ExamGPT-5.2 by 33.737.74+33.7
- SimpleBenchGPT-5.2 by 22.845.823+22.8
- CritPtGPT-5.2 by 11.611.60+11.6
FactsEven
- AA-Omniscience · Non-hallucinationLlama 3.1 Instruct 405B by 28.818.847.6+28.8
- AA-Omniscience · AccuracyGPT-5.2 by 21.144.323.2+21.1
Long documentsGPT-5.2
- AA-LCRGPT-5.2 by 57.482.725.3+57.4
- LongBench v2GPT-5.2 by 18.454.536.1+18.4
Other results8 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)GPT-5.2 by 65.884.819+65.8
- LiveCodeBenchGPT-5.2 by 61.38927.7+61.3
- AA Agentic IndexGPT-5.2 by 53.960.26.3+53.9
- Artificial Analysis Coding IndexGPT-5.2 by 34.248.714.5+34.2
- AA IntelligenceGPT-5.2 by 23.130.47.3+23.1
- AA-OmniscienceGPT-5.2 by 16.2-0.9-17.1+16.2
- MMMLUGPT-5.2 by 15.889.673.8+15.8
- MMLU-ProGPT-5.2 by 13.486.773.3+13.4
Questions people ask
Which is better, GPT-5.2 or Llama 3.1 Instruct 405B?
GPT-5.2 wins five of the six areas where both have results: coding, agents, reasoning, long documents and following instructions. Llama 3.1 Instruct 405B wins none. They are level on facts.
Which is better for coding?
GPT-5.2. It wins 4 of the 4 coding tests both models report; Llama 3.1 Instruct 405B wins none.
How do you compare the two?
We use the 22 benchmark tests both models have published scores on. The verdict counts the 14 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 8 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.