The two are evenly matched.Jamba 1.5 Large is better at reasoning; Qwen2 Instruct (72B) at coding.
Scores updated · 13 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.
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+5.6points ahead
Where Qwen2 Instruct (72B) pulls ahead
- Code for real scientific research problemsSciCode+6.6points ahead
Every test, side by side
All 13 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningJamba 1.5 Large
- GPQA DiamondJamba 1.5 Large by 5.642.737.1+5.6
- Humanity's Last Examtie4.13.7tie
Other results10 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.
- ARC-ChallengeJamba 1.5 Large by 24.19368.9+24.1
- MMLU-ProQwen2 Instruct (72B) by 10.953.564.4+10.9
- MATHQwen2 Instruct (72B) by 9.869.279+9.8
- MMLUQwen2 Instruct (72B) by 8.668.376.9+8.6
- NarrativeQAQwen2 Instruct (72B) by 6.366.472.7+6.3
- GSM8KQwen2 Instruct (72B) by 4.18791.1+4.1
- TruthfulQAJamba 1.5 Large by 3.558.354.8+3.5
- OpenBookQAtie94.895.4tie
- naturalquestions_closedbooktie39.439tie
- AA Intelligencetie66.3tie
Questions people ask
Which is better, Jamba 1.5 Large or Qwen2 Instruct (72B)?
Jamba 1.5 Large and Qwen2 Instruct (72B) each win one of the two areas where both have results. Jamba 1.5 Large wins reasoning; Qwen2 Instruct (72B) wins coding.
Which is better for coding?
Qwen2 Instruct (72B). It wins the one coding test both models report.
How do you compare the two?
We use the 13 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 10 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.