Claude Haiku 4.5 vs JT-35B-Flash
Wins 2 of 6 areas
Long documents · Following instructions
Wins 1 of 6 areas
Agents
Claude Haiku 4.5 wins more areas, narrowly.JT-35B-Flash is better at agents.
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.
- Long documentsFinding answers in very long texts10Claude Haiku 4.51 of 1 test
- Following instructionsDoing exactly what it is asked10Claude Haiku 4.51 of 1 test
- AgentsCarrying out multi-step tasks on its own01JT-35B-Flash1 of 1 test
- CodingWriting and fixing software11Even1 each
- ReasoningHard problems that need careful thinking11Even1 each · 1 tie
- FactsGetting facts right instead of making them up11Even1 each
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 Claude Haiku 4.5 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+36.5points ahead
- Code for real scientific research problemsSciCode+13.1points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+12.3points ahead
Where JT-35B-Flash pulls ahead
- Real work tasks from 44 professionsGDPVal+17points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+15.7points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+6.2points 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.
CodingEven
- SciCodeClaude Haiku 4.5 by 13.142.229.1+13.1
- Terminal-Bench HardJT-35B-Flash by 1.527.328.8+1.5
ReasoningEven
- GPQA DiamondJT-35B-Flash by 15.767.282.9+15.7
- Humanity's Last ExamClaude Haiku 4.5 by 410.46.4+4
- CritPttie00tie
FactsEven
- AA-Omniscience · Non-hallucinationClaude Haiku 4.5 by 36.572.736.2+36.5
- AA-Omniscience · AccuracyJT-35B-Flash by 6.21824.2+6.2
Following instructionsClaude Haiku 4.5
- IFBenchClaude Haiku 4.5 by 12.354.342+12.3
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 44.454.799.1+44.4
- AA Agentic IndexJT-35B-Flash by 4210.352.3+42
- AA-OmniscienceClaude Haiku 4.5 by 19.8-4.4-24.2+19.8
- Artificial Analysis Coding IndexClaude Haiku 4.5 by 1543.928.9+15
- AA IntelligenceJT-35B-Flash by 1.816.918.7+1.8
Questions people ask
Which is better, Claude Haiku 4.5 or JT-35B-Flash?
Claude Haiku 4.5 wins two of the six areas where both have results: long documents and following instructions. JT-35B-Flash wins agents. They are level on coding, reasoning and facts.
Which is better for coding?
Neither. They win 1 coding test each of the 2 both models report.
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.