Claude 3.5 Haiku vs Solar Pro 2
Wins 2 of 6 areas
Long documents · Following instructions
Wins 2 of 6 areas
Coding · Reasoning
The two are evenly matched.Claude 3.5 Haiku is better at long documents and following instructions; Solar Pro 2 at reasoning and coding.
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 thinking02Solar Pro 22 of 3 tests · 1 tie
- CodingWriting and fixing software01Solar Pro 21 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts10Claude 3.5 Haiku1 of 1 test
- Following instructionsDoing exactly what it is asked10Claude 3.5 Haiku1 of 1 test
- AgentsCarrying out multi-step tasks on its own00Even0 each · 1 tie
- FactsGetting facts right instead of making them up11Even1 each
Agents, long documents and following instructions rest on a single test each.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Solar Pro 2 pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+27.9points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+6.8points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+3.8points ahead
Where Claude 3.5 Haiku pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+53.6points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+5.7points 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.
CodingSolar Pro 2
- SciCodeSolar Pro 2 by 2.827.430.2+2.8
- Terminal-Bench Hardtie2.33tie
ReasoningSolar Pro 2
- GPQA DiamondSolar Pro 2 by 27.940.868.7+27.9
- Humanity's Last ExamSolar Pro 2 by 3.83.67.4+3.8
- CritPttie00tie
FactsEven
- AA-Omniscience · Non-hallucinationClaude 3.5 Haiku by 53.658.95.3+53.6
- AA-Omniscience · AccuracySolar Pro 2 by 6.813.219.9+6.8
Following instructionsClaude 3.5 Haiku
- IFBenchClaude 3.5 Haiku by 5.742.837.1+5.7
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.
- AA-OmniscienceClaude 3.5 Haiku by 33.4-22.5-55.9+33.4
- AA Agentic IndexSolar Pro 2 by 9.51.911.4+9.5
- Artificial Analysis Coding IndexClaude 3.5 Haiku by 3.815.912.1+3.8
- τ²-Bench Telecom (AA run)Solar Pro 2 by 3.524.628.1+3.5
- AA IntelligenceClaude 3.5 Haiku by 1.48.97.5+1.4
Questions people ask
Which is better, Claude 3.5 Haiku or Solar Pro 2?
Claude 3.5 Haiku and Solar Pro 2 each win two of the six areas where both have results. Claude 3.5 Haiku wins long documents and following instructions; Solar Pro 2 wins coding and reasoning. They are level on agents and facts.
Which is better for coding?
Solar Pro 2. It wins 1 of the 2 coding tests both models report; Claude 3.5 Haiku wins none, and 1 is a tie.
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.