Claude 3.5 Haiku vs JT-35B-Flash
Wins 0 of 6 areas
—
Wins 4 of 6 areas
Coding · Agents · Reasoning · Long documents
JT-35B-Flash is the stronger all-rounder.
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-35B-Flash2 of 3 tests · 1 tie
- CodingWriting and fixing software02JT-35B-Flash2 of 2 tests
- AgentsCarrying out multi-step tasks on its own01JT-35B-Flash1 of 1 test
- Long documentsFinding answers in very long texts01JT-35B-Flash1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
- Following instructionsDoing exactly what it is asked00Even0 each · 1 tie
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 JT-35B-Flash pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+42.1points ahead
- Reasons across sets of long documentsAA-LCR+38.4points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+26.5points ahead
Where Claude 3.5 Haiku pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+22.7points 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.
CodingJT-35B-Flash
- Terminal-Bench HardJT-35B-Flash by 26.52.328.8+26.5
- SciCodeJT-35B-Flash by 1.727.429.1+1.7
ReasoningJT-35B-Flash
- GPQA DiamondJT-35B-Flash by 42.140.882.9+42.1
- Humanity's Last ExamJT-35B-Flash by 2.83.66.4+2.8
- CritPttie00tie
FactsEven
- AA-Omniscience · Non-hallucinationClaude 3.5 Haiku by 22.758.936.2+22.7
- AA-Omniscience · AccuracyJT-35B-Flash by 1113.224.2+11
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-35B-Flash by 74.524.699.1+74.5
- AA Agentic IndexJT-35B-Flash by 50.41.952.3+50.4
- Artificial Analysis Coding IndexJT-35B-Flash by 1315.928.9+13
- AA IntelligenceJT-35B-Flash by 9.88.918.7+9.8
- AA-OmniscienceClaude 3.5 Haiku by 1.7-22.5-24.2+1.7
Questions people ask
Which is better, Claude 3.5 Haiku or JT-35B-Flash?
JT-35B-Flash wins four of the six areas where both have results: coding, agents, reasoning and long documents. Claude 3.5 Haiku wins none. They are level on facts and following instructions.
Which is better for coding?
JT-35B-Flash. 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 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.