Jamba 1.5 Large wins more areas, narrowly.Jamba 1.5 Mini is cheaper.
Scores updated · 15 tests both models report · How we compare
Where each one wins
Tests won in each of the two 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.
Coding rests on a single test.
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.
Jamba 1.5 Mini costs 94% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Jamba 1.5 Large pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+12.5points ahead
- Code for real scientific research problemsSciCode+8.3points ahead
Where Jamba 1.5 Mini pulls ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+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.
ReasoningEven
- GPQA DiamondJamba 1.5 Large by 12.542.730.2+12.5
- Humanity's Last ExamJamba 1.5 Mini by 14.15.1+1
Other results12 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.
- MATHJamba 1.5 Large by 37.469.231.8+37.4
- Arena HardJamba 1.5 Large by 19.365.446.1+19.3
- GSM8KJamba 1.5 Large by 11.28775.8+11.2
- MMLU-ProJamba 1.5 Large by 1153.542.5+11
- MMLUJamba 1.5 Large by 10.168.358.2+10.1
- NarrativeQAJamba 1.5 Mini by 8.266.474.6+8.2
- ARC-ChallengeJamba 1.5 Large by 7.39385.7+7.3
- WildBenchJamba 1.5 Large by 6.148.542.4+6.1
- OpenBookQAJamba 1.5 Large by 5.894.889+5.8
- TruthfulQAJamba 1.5 Large by 4.258.354.1+4.2
- AA Intelligencetie65.2tie
- naturalquestions_closedbooktie39.438.8tie
Questions people ask
Which is better, Jamba 1.5 Large or Jamba 1.5 Mini?
Jamba 1.5 Large wins one of the two areas where both have results: coding. Jamba 1.5 Mini wins none, but costs 94% less. They are level on reasoning.
Which is better for coding?
Jamba 1.5 Large. It wins the one coding test both models report.
Which is cheaper?
Jamba 1.5 Large costs $2.00 per million input tokens and $8.00 per million output tokens; Jamba 1.5 Mini costs $0.20 and $0.40. That makes Jamba 1.5 Mini about 94% cheaper for the same work.
How do you compare the two?
We use the 15 benchmark tests both models have published scores on. The verdict counts the 3 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 12 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.