Jamba 1.5 Large
Aug 2024
Jamba 1.5 LargeCompare inon
Benchmarks of Jamba 1.5 Large13
BenchmarkByScoreRank
Writing11
Health & law1
Legacy · saturated or no longer reported1
No benchmark matches
—per task?
price not verifiedprice
—output speed?
256Kcontext
Ranking?
Alternatives?
ModelScoreCostPer taskWhat changes
BetterGPT-5 Minihighwins 59%—$0.053
OpenGLM 5.2maxwins 75%—$1.47Memory (4-bit): 239 GB → 452 GBBetterGPT-6 Lunamaxwins 70%—$0.068Function calling only with none · Chat Completions+3BetterGPT-5.6 Lunaxhighwins 70%—$0.085BetterGPT-5.6 Terraxhighwins 72%—$0.63Prompts with >272K input tokensModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
GPT-5 Minihighwins 59%—$0.053GPT-6 Lunamaxwins 70%—$0.068Function calling only with none · Chat Completions+3GPT-5.6 Lunaxhighwins 70%—$0.085GPT-5.6 Terraxhighwins 72%—$0.63Prompts with >272K input tokensGPT-6.1 Solmaxwins 76%—$0.72Remove unsupported parameters+5ModelScoreCostPer taskWhat changes
GLM 5.2maxOpenwins 75%—$1.47Memory (4-bit): 239 GB → 452 GBGLM 5.3maxOpenwins 75%—$2.01Memory (4-bit): 239 GB → 452 GB+4GLM 5unstatedOpenwins 75%—$1 / $3.20Context: 256K → 203K+1GLM 5.1unstatedOpenwins 74%—$1.40 / $4.40Context: 256K → 203K+1GLM 5.3 FlashunstatedOpenwins 73%—$0.15 / $0.50Defaults to max · Self-hosted+4ModelScoreCostPer taskWhat changes
Jamba 1.5 MiniOpenwins 43%——Jamba Reasoning 3BOpenn/a——Jamba 1.7 LargeOpenn/a—$2 / $8Jamba 1.7 MiniOpenn/a——All AI21 Labs models →Run it yourself
estimateFits on✗ 8 GB (phone, laptop)✗ 16 GB✗ 24 GB GPU✗ 48 GB GPU✗ 80 GB GPU
Licencejamba-open-model-licensecommercial use with conditions
Benchmarks
all categoriesChat & Knowledge
Arena Text · overall1,289#162
Arena Text · Chinese1,203#160
Arena Text · English1,266.6#158
Arena Text · German1,199.8#132
Arena Text · instruction following1,212.5#159
Arena Text · Japanese1,118.1#123
Arena Text · non-English1,196.3#163
Arena Text · Russian1,195.7#163
Vals LegalBench74.2#78
Arena Text · overall · full cohort1,237#157
MMLU-Pro · official board49.5#16
Writing & Language
Arena Text · creative writing1,261#154
Arena Text · creative writing · full cohort1,211.6#156
FAQ
How much does Jamba 1.5 Large cost?›
There is no per-unit API price: price not verified.
How good is Jamba 1.5 Large, and what is it best at?›
#162 of 196 in Chat & Knowledge, #154 of 195 in Writing & Language.
Is Jamba 1.5 Large better than Granite 4.1 8B?›
On Arena Text · creative writing, Jamba 1.5 Large scores 1,261 vs 1,263 — about the same.
What is the context window of Jamba 1.5 Large?›
256K tokens.
When was Jamba 1.5 Large released? Is there a newer version?›
Released 2024-08-22. It is the current version in its line.
Is Jamba 1.5 Large open source?›
Yes, the weights are open (jamba-open-model-license licence).
Can I run Jamba 1.5 Large locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Jamba 1.5 Large read images?›
No, it accepts text only.
What is Jamba 1.5 Large?›
Jamba 1.5 Large is an open-weights language model from AI21 Labs, released Aug 2024.
What are the best alternatives to Jamba 1.5 Large?›
GPT-5 Mini (better), GLM 5.2 (open weights).