Claude 3 Haiku vs Solar Open 100B (Reasoning)
Wins 1 of 6 areas
Facts
Wins 5 of 6 areas
Coding · Agents · Reasoning · Long documents · Following instructions
Solar Open 100B (Reasoning) is the stronger all-rounder.Claude 3 Haiku is better at facts.
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 Open 100B (Reasoning)2 of 3 tests · 1 tie
- CodingWriting and fixing software02Solar Open 100B (Reasoning)2 of 2 tests
- AgentsCarrying out multi-step tasks on its own01Solar Open 100B (Reasoning)1 of 1 test
- Long documentsFinding answers in very long texts01Solar Open 100B (Reasoning)1 of 1 test
- Following instructionsDoing exactly what it is asked01Solar Open 100B (Reasoning)1 of 1 test
- FactsGetting facts right instead of making them up10Claude 3 Haiku1 of 2 tests · 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 Solar Open 100B (Reasoning) pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+28.3points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+21.6points ahead
- Reasons across sets of long documentsAA-LCR+13.3points ahead
Where Claude 3 Haiku pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+9.1points 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 Open 100B (Reasoning)
- SciCodeSolar Open 100B (Reasoning) by 8.318.626.9+8.3
- Terminal-Bench HardSolar Open 100B (Reasoning) by 1.50.82.3+1.5
AgentsSolar Open 100B (Reasoning)
- GDPValSolar Open 100B (Reasoning) by 8.208.2+8.2
ReasoningSolar Open 100B (Reasoning)
- GPQA DiamondSolar Open 100B (Reasoning) by 28.337.465.7+28.3
- Humanity's Last ExamSolar Open 100B (Reasoning) by 6.34.110.4+6.3
- CritPttie00tie
FactsClaude 3 Haiku
- AA-Omniscience · Non-hallucinationClaude 3 Haiku by 9.119.510.4+9.1
- AA-Omniscience · Accuracytie17.618.5tie
Long documentsSolar Open 100B (Reasoning)
- AA-LCRSolar Open 100B (Reasoning) by 13.327.741+13.3
Following instructionsSolar Open 100B (Reasoning)
- IFBenchSolar Open 100B (Reasoning) by 21.636.157.7+21.6
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)Solar Open 100B (Reasoning) by 27.121.148.2+27.1
- AA Agentic IndexSolar Open 100B (Reasoning) by 17.3724.3+17.3
- AA-OmniscienceClaude 3 Haiku by 5.9-48.6-54.5+5.9
- AA IntelligenceSolar Open 100B (Reasoning) by 4.85.610.4+4.8
- Artificial Analysis Coding IndexSolar Open 100B (Reasoning) by 3.86.710.5+3.8
Questions people ask
Which is better, Claude 3 Haiku or Solar Open 100B (Reasoning)?
Solar Open 100B (Reasoning) wins five of the six areas where both have results: coding, agents, reasoning, long documents and following instructions. Claude 3 Haiku wins facts.
Which is better for coding?
Solar Open 100B (Reasoning). 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.