Claude 3 Haiku vs Llama Nemotron Super 49B V1.5
Wins 1 of 6 areas
Long documents
Wins 3 of 6 areas
Coding · Reasoning · Facts
Llama Nemotron Super 49B V1.5 wins more areas, narrowly.Claude 3 Haiku is better at long documents.
Scores updated · 15 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.
- ReasoningHard problems that need careful thinking02Llama Nemotron Super 49B V1.52 of 3 tests · 1 tie
- CodingWriting and fixing software02Llama Nemotron Super 49B V1.52 of 2 tests
- FactsGetting facts right instead of making them up01Llama Nemotron Super 49B V1.51 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts10Claude 3 Haiku1 of 1 test
- AgentsCarrying out multi-step tasks on its own00Even0 each · 1 tie
- Following instructionsDoing exactly what it is asked00Even0 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 tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Llama Nemotron Super 49B V1.5 pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+37.4points ahead
- Code for real scientific research problemsSciCode+16.2points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+4.5points ahead
Where Claude 3 Haiku pulls ahead
- Reasons across sets of long documentsAA-LCR+3points ahead
Every test, side by side
All 15 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingLlama Nemotron Super 49B V1.5
- SciCodeLlama Nemotron Super 49B V1.5 by 16.218.634.8+16.2
- Terminal-Bench HardLlama Nemotron Super 49B V1.5 by 4.50.85.3+4.5
ReasoningLlama Nemotron Super 49B V1.5
- GPQA DiamondLlama Nemotron Super 49B V1.5 by 37.437.474.8+37.4
- Humanity's Last ExamLlama Nemotron Super 49B V1.5 by 3.24.17.3+3.2
- CritPttie00tie
FactsLlama Nemotron Super 49B V1.5
- AA-Omniscience · Non-hallucinationLlama Nemotron Super 49B V1.5 by 2.319.521.8+2.3
- AA-Omniscience · Accuracytie17.617.2tie
Other results5 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.
- Artificial Analysis Coding IndexLlama Nemotron Super 49B V1.5 by 8.46.715.1+8.4
- τ²-Bench Telecom (AA run)Llama Nemotron Super 49B V1.5 by 721.128.1+7
- AA IntelligenceLlama Nemotron Super 49B V1.5 by 3.45.69+3.4
- AA Agentic IndexLlama Nemotron Super 49B V1.5 by 2.479.4+2.4
- AA-OmniscienceLlama Nemotron Super 49B V1.5 by 1-48.6-47.6+1
Questions people ask
Which is better, Claude 3 Haiku or Llama Nemotron Super 49B V1.5?
Llama Nemotron Super 49B V1.5 wins three of the six areas where both have results: coding, reasoning and facts. Claude 3 Haiku wins long documents. They are level on agents and following instructions.
Which is better for coding?
Llama Nemotron Super 49B V1.5. It wins 2 of the 2 coding tests both models report; Claude 3 Haiku wins none.
How do you compare the two?
We use the 15 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 5 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.