Claude 3.5 Haiku vs Nex-N2-Pro
Wins 0 of 6 areas
—
Wins 5 of 6 areas
Coding · Agents · Reasoning · Long documents · Following instructions
Nex-N2-Pro is the stronger all-rounder.
Scores updated · 16 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 thinking03Nex-N2-Pro3 of 3 tests
- CodingWriting and fixing software02Nex-N2-Pro2 of 2 tests
- AgentsCarrying out multi-step tasks on its own02Nex-N2-Pro2 of 2 tests
- Long documentsFinding answers in very long texts01Nex-N2-Pro1 of 1 test
- Following instructionsDoing exactly what it is asked01Nex-N2-Pro1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
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 Nex-N2-Pro pulls ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+57.7points ahead
- Reasons across sets of long documentsAA-LCR+54.4points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+48.4points ahead
Where Claude 3.5 Haiku pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+53.8points ahead
Every test, side by side
All 16 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingNex-N2-Pro
- Terminal-Bench 2.1Nex-N2-Pro by 57.710.167.8+57.7
- SciCodeNex-N2-Pro by 15.927.443.3+15.9
AgentsNex-N2-Pro
- GDPValNex-N2-Pro by 30.3030.3+30.3
- τ-Bench V3 · BankingNex-N2-Pro by 11.75.817.5+11.7
ReasoningNex-N2-Pro
- GPQA DiamondNex-N2-Pro by 48.440.889.2+48.4
- Humanity's Last ExamNex-N2-Pro by 30.13.633.7+30.1
- CritPtNex-N2-Pro by 8.608.6+8.6
FactsEven
- AA-Omniscience · Non-hallucinationClaude 3.5 Haiku by 53.858.95.1+53.8
- AA-Omniscience · AccuracyNex-N2-Pro by 21.613.234.8+21.6
Following instructionsNex-N2-Pro
- IFBenchNex-N2-Pro by 23.442.866.2+23.4
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.
- τ²-Bench Telecom (AA run)Nex-N2-Pro by 5724.681.6+57
- Artificial Analysis Coding IndexNex-N2-Pro by 43.215.959.1+43.2
- AA Agentic IndexNex-N2-Pro by 29.31.931.2+29.3
- AA IntelligenceNex-N2-Pro by 19.38.928.2+19.3
- AA-OmniscienceClaude 3.5 Haiku by 4.5-22.5-27.1+4.5
Questions people ask
Which is better, Claude 3.5 Haiku or Nex-N2-Pro?
Nex-N2-Pro wins five of the six areas where both have results: coding, agents, reasoning, long documents and following instructions. Claude 3.5 Haiku wins none. They are level on facts.
Which is better for coding?
Nex-N2-Pro. It wins 2 of the 2 coding tests both models report; Claude 3.5 Haiku wins none.
How do you compare the two?
We use the 16 benchmark tests both models have published scores on. The verdict counts the 11 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.