Skip to content
Model Pareto

Jamba 1.7 Large

AI21 LabsOpen weightsartificialanalysis.ai ↗
Input
—
Output
—
Speed
~72tok/sest.
Context
256Ktokens

Long-tail import from Artificial Analysis (2026-09-24); AA variant: Jamba 1.7 Large. Price = AA median host price.

Rankings

Self-hostingEstimated

How we estimate →

What it would cost to run these open weights yourself on rented GPUs. No API sells this model, so this is its price on the chart.

Hardware
4× B200 180GB
FP8 weights
Throughput
~5,485 tok/s
many requests batched
Price
$0.55–4.92 /M tok
busy → light use
On your own machine
Mac Studio M5 Ultra 512GB (int4, ~18 tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • FP8 weights (398.6B params, 94B active per token) + 25% KV-cache headroom ≈ 498 GB
  • 4× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
  • ~5,485 output tok/s aggregate at batch 157 (bandwidth-bound); MoE compute scales with active params
  • Blended 3:1 input:output; prefill ~45,239 tok/s
  • Low = 75% utilization at the low GPU price; high = 20% at the high price

Benchmark scores

~ italic, dashed = no published score yet, estimated from related benchmarks.

Writing & chat

MMMLUEstimated
~last of 5 (estimated)below measured range (<81.3%)
  1. #1Gemini 3.1 Pro92.6%
  2. #2Gemma 4 31B88.4%
  3. #4gpt-oss-120b81.3%
  4. ~#5Jamba 1.7 LargeEstimated<81.3%
No published score — estimated from related benchmarks
~#52 of 57 (estimated)~1322 Elo
  1. #1Gemini 4 Argon1525
  2. #2Claude Opus 5.51507
  3. #51Molmo2-8BFew votes1322
  4. ~#52Jamba 1.7 LargeEstimated1322
  5. #52Ring-flash-2.01321
No published score — estimated from related benchmarks
~#22 of 26 (estimated)~1436 Elo
  1. #1GPT-6 Astra2173
  2. #2Claude Fable 5.12162
  3. #21Gemini 3.1 Pro1491
  4. ~#22Jamba 1.7 LargeEstimated1436
  5. #22Mistral Large 31412
No published score — estimated from related benchmarks

Hard reasoning

Agents

OSWorld 2.0Estimated
~#3 of 5 (estimated)~53.8%
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. ~#3Jamba 1.7 LargeEstimated53.8%
  4. #3GPT-5.6 Terra50.2%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#21 of 22 (estimated)~33.4%
  1. #1Atria Dawn Preview92.5%
  2. #2GPT-6 Astra91.5%
  3. #20Nemotron 3 Ultra44.4%
  4. ~#21Jamba 1.7 LargeEstimated33.4%
  5. #21Mistral Small 421.3%
No published score — estimated from related benchmarks
~#60 of 92 (estimated)~705 Elo
  1. #1Claude Opus 5.51866
  2. #2Muse Wonder Full1857
  3. #59Claude Haiku 4.5719
  4. ~#60Jamba 1.7 LargeEstimated705
  5. #60MiniCPM5-2B694
No published score — estimated from related benchmarks
~#79 of 85 (estimated)~0.3%
  1. #1Claude Fable 5.276.4%
  2. #2Muse Wonder Full71.3%
  3. #77Granite 4.2 3B0.4%
  4. ~#79Jamba 1.7 LargeEstimated0.3%
  5. #79gpt-oss-120b0.2%
No published score — estimated from related benchmarks
~last of 91 (estimated)below measured range (<3.3%)
  1. #1Muse Spark 1.350.5%
  2. #2GLM-5.350.3%
  3. #90Llama 4 Scout3.3%
  4. ~#91Jamba 1.7 LargeEstimated<3.3%
No published score — estimated from related benchmarks