Compare / ai21-jamba-large-1.7 vs Claude Haiku 4.5

ai21-jamba-large-1.7 vs Claude Haiku 4.5

5 results from 2 sources that measured both models. Each row is in the source's own units; there is no overall winner.

ai21-jamba-large-1.7
AI21 Labs · profile
Claude Haiku 4.5
Anthropic · profile
Results compared
5
Shared sources
2
BenchmarkMetricai21-jamba-large-1.7Claude Haiku 4.5
UGI LeaderboardreportedRequested-length error% off the requested word count 20.0%6.0%
UGI LeaderboardreportedStyle adherencescore from 0 to 1 0.360.39
UGI LeaderboardreportedWriting scorescore out of 100 38.052.2
Vectara Hallucination LeaderboardreportedAnswer rate% of documents 98.9%99.5%
Vectara Hallucination LeaderboardreportedHallucination rate% of summaries 9.7%9.8%

Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.