GPT-4o vs Llama 3.1 Nemotron Ultra 253B V1
Wins 2 of 6 areas
Facts · Long documents
Wins 2 of 6 areas
Reasoning · Following instructions
The two are evenly matched.GPT-4o is better at facts and long documents; Llama 3.1 Nemotron Ultra 253B V1 at reasoning and following instructions.
Scores updated · 19 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.
- FactsGetting facts right instead of making them up20GPT-4o2 of 2 tests
- Long documentsFinding answers in very long texts10GPT-4o1 of 1 test
- ReasoningHard problems that need careful thinking02Llama 3.1 Nemotron Ultra 253B V12 of 3 tests · 1 tie
- Following instructionsDoing exactly what it is asked01Llama 3.1 Nemotron Ultra 253B V11 of 1 test
- CodingWriting and fixing software11Even1 each
- 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.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where GPT-4o pulls ahead
- Reasons across sets of long documentsAA-LCR+48.3points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+43.3points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+6points ahead
Where Llama 3.1 Nemotron Ultra 253B V1 pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+20.2points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+5.6points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+2.2points ahead
Every test, side by side
All 19 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingEven
- Terminal-Bench HardGPT-4o by 68.32.3+6
- SciCodeLlama 3.1 Nemotron Ultra 253B V1 by 1.433.334.7+1.4
ReasoningLlama 3.1 Nemotron Ultra 253B V1
- GPQA DiamondLlama 3.1 Nemotron Ultra 253B V1 by 20.252.672.8+20.2
- Humanity's Last ExamLlama 3.1 Nemotron Ultra 253B V1 by 5.61.87.4+5.6
- CritPttie00tie
FactsGPT-4o
- AA-Omniscience · Non-hallucinationGPT-4o by 43.362.118.8+43.3
- AA-Omniscience · AccuracyGPT-4o by 3.623.720.1+3.6
Following instructionsLlama 3.1 Nemotron Ultra 253B V1
- IFBenchLlama 3.1 Nemotron Ultra 253B V1 by 2.23638.2+2.2
Other results9 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.
- AIME 2025Llama 3.1 Nemotron Ultra 253B V1 by 60.811.772.5+60.8
- AA-OmniscienceGPT-4o by 34.4-10.5-44.9+34.4
- LiveCodeBenchLlama 3.1 Nemotron Ultra 253B V1 by 2838.366.3+28
- MATH-500 (EM)Llama 3.1 Nemotron Ultra 253B V1 by 22.474.697+22.4
- τ²-Bench Telecom (AA run)GPT-4o by 17.528.911.4+17.5
- Artificial Analysis Coding IndexGPT-4o by 11.124.213.1+11.1
- IFEvalLlama 3.1 Nemotron Ultra 253B V1 by 8.58189.5+8.5
- AA Agentic IndexGPT-4o by 4.68.43.8+4.6
- AA Intelligencetie7.37.5tie
Questions people ask
Which is better, GPT-4o or Llama 3.1 Nemotron Ultra 253B V1?
GPT-4o and Llama 3.1 Nemotron Ultra 253B V1 each win two of the six areas where both have results. GPT-4o wins facts and long documents; Llama 3.1 Nemotron Ultra 253B V1 wins reasoning and following instructions. They are level on coding and agents.
Which is better for coding?
Neither. They win 1 coding test each of the 2 both models report.
How do you compare the two?
We use the 19 benchmark tests both models have published scores on. The verdict counts the 10 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 9 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.