Jamba 1.5 Large

AI21 Labs

Verified against Artificial Analysis · Jul 13, 2026

Capability

percentile index

Price /M

$2 / $8

in / out

Context

—

Avg score

32.5

6 benchmarks

AA Intelligence

5.1

index

Weights

Closed

Released

Aug 22, 2024

About

Jamba 1.5 Large is a proprietary model in the Jamba family from AI21 Labs. Benchmarked on 6 evals, averaging 32.5.

Benchmark scores · 6

avg 32.5 — higher is better

MATHartificial-analysis · 2026-07

60.6

MMLU-Proartificial-analysis · 2026-07

57.2

GPQA Diamondartificial-analysis · 2026-07

42.7

SciCodeartificial-analysis · 2026-07

16.3

LiveCodeBenchartificial-analysis · 2026-07

14.3

Humanity's Last Examartificial-analysis · 2026-07

Details

PublisherAI21 Labs

FamilyJamba

Parameters—

License—

WeightsClosed

ReleasedAug 22, 2024

Performance & price

Price in / out$2 / $8 per 1M

Blended price$3.5 / 1M

Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →

History

full ledger →

Capability over time

Append-only ledger — every observed change to this model's numbers.

API providers

Artificial Analysis$8/M