Claude 3 Haiku vs JT-MINI
Wins 2 of 6 areas
Facts · Long documents
Wins 3 of 6 areas
Coding · Agents · Reasoning
JT-MINI wins more areas, narrowly.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 thinking02JT-MINI2 of 3 tests · 1 tie
- CodingWriting and fixing software02JT-MINI2 of 2 tests
- AgentsCarrying out multi-step tasks on its own01JT-MINI1 of 1 test
- FactsGetting facts right instead of making them up20Claude 3 Haiku2 of 2 tests
- Long documentsFinding answers in very long texts10Claude 3 Haiku1 of 1 test
- 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 three tests each model wins by the widest margin. Scores are out of 100.
Where JT-MINI pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+30.2points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+17.4points ahead
- Code for real scientific research problemsSciCode+8.6points ahead
Where Claude 3 Haiku pulls ahead
- Reasons across sets of long documentsAA-LCR+14.7points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+10.8points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+3.4points 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.
CodingJT-MINI
- Terminal-Bench HardJT-MINI by 17.40.818.2+17.4
- SciCodeJT-MINI by 8.618.627.2+8.6
ReasoningJT-MINI
- GPQA DiamondJT-MINI by 30.237.467.6+30.2
- Humanity's Last ExamJT-MINI by 2.34.16.4+2.3
- CritPttie00tie
FactsClaude 3 Haiku
- AA-Omniscience · Non-hallucinationClaude 3 Haiku by 10.819.58.7+10.8
- AA-Omniscience · AccuracyClaude 3 Haiku by 3.417.614.2+3.4
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)JT-MINI by 71.921.193+71.9
- AA Agentic IndexJT-MINI by 35.4742.4+35.4
- AA-OmniscienceClaude 3 Haiku by 15.5-48.6-64.1+15.5
- Artificial Analysis Coding IndexJT-MINI by 14.56.721.2+14.5
- AA IntelligenceJT-MINI by 6.65.612.2+6.6
Questions people ask
Which is better, Claude 3 Haiku or JT-MINI?
JT-MINI wins three of the six areas where both have results: coding, agents and reasoning. Claude 3 Haiku wins facts and long documents. They are level on following instructions.
Which is better for coding?
JT-MINI. 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.