Models/Jamba 1.7 Large

MDL

Jamba 1.7 Large

AI21 Labs

Verified against Artificial Analysis · Jul 13, 2026

Capability

percentile index

Price /M

$2 / $8

in / out

Context

—

Avg score

24.4

11 benchmarks

AA Intelligence

5.3

index

Speed

58 tok/s

TTFT 0.7s

Released

Jul 7, 2025

About

Jamba 1.7 Large is a proprietary model in the Jamba family from AI21 Labs. Benchmarked on 11 evals, averaging 24.4.

Benchmark scores · 11

avg 24.4 — higher is better

MATHartificial-analysis · 2026-07

MMLU-Proartificial-analysis · 2026-07

57.7

GPQA Diamondartificial-analysis · 2026-07

IFBenchartificial-analysis · 2026-07

35.2

SciCodeartificial-analysis · 2026-07

18.8

LiveCodeBenchartificial-analysis · 2026-07

18.1

AA Long-Context Reasoningartificial-analysis · 2026-07

17.3

τ²-benchartificial-analysis · 2026-07

13.5

Humanity's Last Examartificial-analysis · 2026-07

3.8

Terminal-Bench Hardartificial-analysis · 2026-07

2.3

AIMEartificial-analysis · 2026-07

2.3

Details

PublisherAI21 Labs

FamilyJamba

Parameters—

License—

WeightsClosed

ReleasedJul 7, 2025

Performance & price

Output speed58 tok/s

Latency (TTFT)0.7s

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

Blended price$3.5 / 1M

Math index2.3

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