AI21Language modelLimited access
Jamba Mini 1.7
Jamba Mini 1.7 has no overall index value yet because there are too few independent benchmark results.
PopularityRank 504 of 875
28out of 100+1 vs. last month
Summary
Jamba Mini 1.7 improves source-grounded answers and instruction following, according to AI21. The provider reports a FACTS score of 0.790, compared with 0.727 for version 1.6. The hybrid model retains a 256K context window.
The weights use the Jamba Open Model License. Hugging Face requires accepting the terms and sharing contact information. AI21 documents at least two GPUs with 80 GB of memory each for BF16 deployment with up to 200K context tokens.
All benchmark results
Every published result with its source, test setup and comparison models.
Show all 9 published benchmark results
Measurements without matching peer values
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
CritPt v2: Overall (Show measurement, test conditions, and source)
- Source value
- 0
- Score
- 0
- Metric
- pass@1 accuracy
- Unit
- %
- Benchmark version
- v2
- Category
- reasoning
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- disputed
- Retrieved at
- 2026-11-02
- Methodology
- Exact AA configuration: Jamba 1.7 Mini (release jamba-1-7-mini, row jamba-1-7-mini, UUID b4f14013-37dd-4c75-bd8a-378365d9ed77, reasoning=false, effort=not specified, suffix=not specified). AA marks this model variant as non-reasoning and reports 0 reasoning tokens. The full CritPt v2 run covers 70 questions with five repeats. The official grading server reports pass@1.. Source model ID: artificial-analysis/b4f14013-37dd-4c75-bd8a-378365d9ed77/jamba-1-7-mini/jamba-1-7-mini. Source model name: Jamba Mini 1.7. Provider reported by source: AI21 Labs. Model snapshot: Jamba 1.7 Mini. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Tool policy: Python functions, symbolic expressions, and numerical answers; official grading server. Attempts: 70 questions, five repeats per question, pass@1. Reasoning: non-reasoning. Reasoning effort: none. Score display: 0.0%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-02-67d46be20a5b. Source payload hash: 67d46be20a5b412db6cfb60ad190441fcaa5513500b8fd47d033168d0e97b6b2. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-11-02. Source cohort: artificial-analysis-critpt-v2:v2:standalone:non-reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Jamba 1.7 Mini (release jamba-1-7-mini, row jamba-1-7-mini, UUID b4f14013-37dd-4c75-bd8a-378365d9ed77, reasoning=false, effort=not specified, suffix=not specified). AA marks this model variant as non-reasoning and reports 0 reasoning tokens. The full CritPt v2 run covers 70 questions with five repeats. The official grading server reports pass@1.. Tool policy: Python functions, symbolic expressions, and numerical answers; official grading server. Attempts: 70 questions, five repeats per question, pass@1. Reasoning: non-reasoning. Reasoning effort: none
- Context
- This AA source field contains the original CritPt score. The earlier CritPt v2 attribution was incorrect; the value and former label remain as disputed historical evidence.. The source dataset marks this result as disputed. It remains visible as documented evidence, but is not reliable comparative proof.
IFBench: Overall (Show measurement, test conditions, and source)
- Source value
- 31.360544217687096
- Score
- 31.360544217687096
- Metric
- IFBench prompt-level loose accuracy (pass@1)
- Unit
- %
- Benchmark version
- AA test set: 294 questions
- Category
- general
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- superseded
- Retrieved at
- 2026-11-02
- Methodology
- Exact AA configuration: Jamba 1.7 Mini (release jamba-1-7-mini, row jamba-1-7-mini, UUID b4f14013-37dd-4c75-bd8a-378365d9ed77, reasoning=false, effort=not specified, suffix=not specified). AA marks this model variant as non-reasoning and reports 0 reasoning tokens. Artificial Analysis runs 294 questions from the IFBench test set with five repeats per question. The official evaluator scores prompt-level accuracy in loose mode as pass@1.. Source model ID: artificial-analysis/b4f14013-37dd-4c75-bd8a-378365d9ed77/jamba-1-7-mini/jamba-1-7-mini. Source model name: Jamba Mini 1.7. Provider reported by source: AI21 Labs. Model snapshot: Jamba 1.7 Mini. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Tool policy: Single-turn answer evaluated with the official IFBench source code. Attempts: pass@1, 5 repeats per question. Reasoning: non-reasoning. Reasoning effort: none. Score display: 31.4%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-02-67d46be20a5b. Source payload hash: 67d46be20a5b412db6cfb60ad190441fcaa5513500b8fd47d033168d0e97b6b2. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-11-02. Source cohort: artificial-analysis-ifbench:AA test set: 294 questions:standalone:non-reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Jamba 1.7 Mini (release jamba-1-7-mini, row jamba-1-7-mini, UUID b4f14013-37dd-4c75-bd8a-378365d9ed77, reasoning=false, effort=not specified, suffix=not specified). AA marks this model variant as non-reasoning and reports 0 reasoning tokens. Artificial Analysis runs 294 questions from the IFBench test set with five repeats per question. The official evaluator scores prompt-level accuracy in loose mode as pass@1.. Tool policy: Single-turn answer evaluated with the official IFBench source code. Attempts: pass@1, 5 repeats per question. Reasoning: non-reasoning. Reasoning effort: none
- Context
- The often cited 58 refers to verifiable out-of-domain constraint types, not the number of questions in AA's test run.. This result is retained as historical evidence and is not interchangeable with current results.
IFBench: Overall (Show measurement, test conditions, and source)
- Source value
- 31.360544217687096
- Score
- 31.360544217687096
- Metric
- IFBench prompt-level loose accuracy (pass@1)
- Unit
- %
- Benchmark version
- AA test set: 294 questions
- Category
- general
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-11-06
- Methodology
- Exact AA configuration: Jamba 1.7 Mini (release jamba-1-7-mini, row jamba-1-7-mini, UUID b4f14013-37dd-4c75-bd8a-378365d9ed77, reasoning=false, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count. Artificial Analysis runs 294 questions from the IFBench test set with five repeats per question. The official evaluator scores prompt-level accuracy in loose mode as pass@1.. Source model ID: artificial-analysis/b4f14013-37dd-4c75-bd8a-378365d9ed77/jamba-1-7-mini/jamba-1-7-mini. Source model name: Jamba Mini 1.7. Provider reported by source: AI21 Labs. Model snapshot: Jamba 1.7 Mini. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Tool policy: Single-turn answer evaluated with the official IFBench source code. Attempts: pass@1, 5 repeats per question. Reasoning: non-reasoning. Reasoning effort: none. Score display: 31.4%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-06-ec1194e008b3. Source payload hash: ec1194e008b3638ef60dbf5249daf9e6047364e22905e745a4af64c5f3f080fe. Parser version: artificial-analysis-rsc-models-v4. Imported at: 2026-11-06. Source cohort: artificial-analysis-ifbench:AA test set: 294 questions:standalone:non-reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Jamba 1.7 Mini (release jamba-1-7-mini, row jamba-1-7-mini, UUID b4f14013-37dd-4c75-bd8a-378365d9ed77, reasoning=false, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count. Artificial Analysis runs 294 questions from the IFBench test set with five repeats per question. The official evaluator scores prompt-level accuracy in loose mode as pass@1.. Tool policy: Single-turn answer evaluated with the official IFBench source code. Attempts: pass@1, 5 repeats per question. Reasoning: non-reasoning. Reasoning effort: none
- Context
- The often cited 58 refers to verifiable out-of-domain constraint types, not the number of questions in AA's test run.
Kagi Offline Benchmark (Show measurement, test conditions, and source)
- Source value
- 11.7
- Score
- 11.7
- Metric
- Accuracy (%)
- Unit
- %
- Benchmark version
- Kagi task-list revision 2026-02-13; current page observed 2026-10-17
- Category
- general-reasoning
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Kagi LLM Benchmarking Project
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Independent evaluation. Kagi Offline Benchmark without tools. Exact listed route: ai21/jamba-mini-1.7, provider OpenRouter. Kagi says its task list was last revised 2026-02-13 and the test favors models that use chain of thought heavily. The source does not state this row's immutable served checkpoint, reasoning setting, per-model sample count, confidence interval, or execution date.
- Context
- This is a route-level result, not a claim about a pinned Jamba Mini 1.7 weight or snapshot. Do not treat it as resolving the separate 2025-07 checkpoint versus 2025-08 API identity discrepancy recorded in earlier research. Unknown configuration and sample details remain unpublished.
FACTS (Show measurement, test conditions, and source)
- Source value
- 0.79
- Score
- 0.79
- Metric
- FACTS
- Unit
- No unit provided
- Category
- hallucination
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- AI21 Jamba Mini 1.7 model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Exact Jamba Mini 1.7 column in AI21's Grounding and instruction-following improvements table; FACTS grounding result. Benchmark-specific serving and evaluation settings are not documented.
- Context
- Vendor-reported raw score with an unspecified scale, not normalized to a percentage. Exact benchmark version, harness, sample count, sampling, reasoning setting, and run date are not supplied. Inference examples are not the benchmark protocol.
IFEcal (Show measurement, test conditions, and source)
- Source value
- 0.76
- Score
- 0.76
- Metric
- IFEcal
- Unit
- No unit provided
- Category
- instruction-following
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- AI21 Jamba Mini 1.7 model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Exact Jamba Mini 1.7 column in AI21's Grounding and instruction-following improvements table; steerability result labelled IFEcal in the source. Benchmark-specific serving and evaluation settings are not documented.
- Context
- Vendor-reported raw score with an unspecified scale. The source spells the benchmark IFEcal; no equivalence to IFEval is established. Exact version, harness, sample count, sampling, reasoning setting, and run date are not supplied. Inference examples are not the benchmark protocol.
VikiKaynak DSSI pipeline style BLEU (Show measurement, test conditions, and source)
- Source value
- 79.4
- Score
- 79.4
- Metric
- BLEU style-similarity score, reported out of 100
- Unit
- points
- Benchmark version
- SIGTURK 2026 Table 7, DSSI pipeline, exact Hugging Face checkpoint
- Category
- language
- Direction
- Higher is better
- Sample
- 274
- Source type
- independent-evaluator
- Evaluator
- Directed Attention is All You Need: Profiling Style from Limited Text Data (SIGTURK 2026)
- Status
- active
- Retrieved at
- 2026-10-16
- Methodology
- Independent evaluation. Exact Hugging Face checkpoint ai21labs/AI21-Jamba-Mini-1.7; VikiKaynak Turkish corpus, 274 documents; DSSI pipeline uses back-translation, style extraction, prompt optimization and Rule+Example style imitation.
- Context
- System-level result for the named Hugging Face checkpoint. The paper does not pin an immutable repository revision or establish a dated API alias; DSSI pipeline scores are not native standalone-model scores.
VikiKaynak zero-shot baseline style BLEU (Show measurement, test conditions, and source)
- Source value
- 51.5
- Score
- 51.5
- Metric
- BLEU style-similarity score, reported out of 100
- Unit
- points
- Benchmark version
- SIGTURK 2026 Table 7, zero-shot baseline, exact Hugging Face checkpoint
- Category
- language
- Direction
- Higher is better
- Sample
- 274
- Source type
- independent-evaluator
- Evaluator
- Directed Attention is All You Need: Profiling Style from Limited Text Data (SIGTURK 2026)
- Status
- active
- Retrieved at
- 2026-10-16
- Methodology
- Independent evaluation. Exact Hugging Face checkpoint ai21labs/AI21-Jamba-Mini-1.7; VikiKaynak Turkish corpus, 274 documents; standard zero-shot prompt without DSSI prompt optimization.
- Context
- System-level result for the named Hugging Face checkpoint. The paper does not pin an immutable repository revision or establish a dated API alias; DSSI pipeline scores are not native standalone-model scores.
VikiKaynak DSSI pipeline content BERT (Show measurement, test conditions, and source)
- Source value
- 96.9
- Score
- 96.9
- Metric
- BERT content-preservation score, reported out of 100
- Unit
- points
- Benchmark version
- SIGTURK 2026 Table 7, DSSI pipeline, exact Hugging Face checkpoint
- Category
- language
- Direction
- Higher is better
- Sample
- 274
- Source type
- independent-evaluator
- Evaluator
- Directed Attention is All You Need: Profiling Style from Limited Text Data (SIGTURK 2026)
- Status
- active
- Retrieved at
- 2026-10-16
- Methodology
- Independent evaluation. Exact Hugging Face checkpoint ai21labs/AI21-Jamba-Mini-1.7; VikiKaynak Turkish corpus, 274 documents; DSSI pipeline uses back-translation, style extraction, prompt optimization and Rule+Example style imitation.
- Context
- System-level result for the named Hugging Face checkpoint. The paper does not pin an immutable repository revision or establish a dated API alias; DSSI pipeline scores are not native standalone-model scores.
Popularity compared
How often the model is searched for, used and mentioned, compared with every model of its category.
Popularity index
The 100 most popular models of this category, 0 to 100, higher is more popular
20 of 101 models
Gemini 4 Argon, Google DeepMind: 92
GPT-6 Astra, OpenAI: 78
Claude Haiku 5.5, Anthropic: 77
Qwen3.5 4B, Alibaba: 76
GPT-5, OpenAI: 73
GPT-6 Sol, OpenAI: 72
Qwen3.5 0.8B, Alibaba: 72
Qwen3.5 2B, Alibaba: 71
Qwen 3.8 27B, Alibaba: 70
Claude Opus 5.5, Anthropic: 70
DeepSeek V4.1 Flash 1017, DeepSeek: 68
Qwen 3.8 Max 0902, Alibaba: 68
Kimi K3, Moonshot AI: 68
DeepSeek-V4-Flash, DeepSeek: 65
GPT-5.6 Terra, OpenAI: 64
Claude Sonnet 5, Anthropic: 63
DiffusionGemma 26B A4B IT, Google: 63
Claude Opus 5, Anthropic: 62
Qwen 3.8 Flash, Alibaba: 62
Jamba Mini 1.7, AI21: 28
As of November 2026 · Source: gradually.ai popularity index
Over time
Weekly values from October 18, 2026 to November 5, 2026
Jamba Mini 1.7Falcon 3 10BGLM-4.7-FlashXMiniMax-M2.7-highspeedOLMo 2 13B
All specifications
Architecture
Input and output
Watermarking and provenance
AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.
- AI watermarking
- Unknown
- no source
- Watermarking technique
- Not known
- no source
Licence and access
Frequently asked questions about Jamba Mini 1.7
How large is the context window of Jamba Mini 1.7?
256,000 tokens. That is how much text Jamba Mini 1.7 reads at once, about 380 A4 pages.
Page count as a rule of thumb from Artificial Analysis
Kimi K2.6262K
Qwen 3.8 27B262K
Kimi K2.7 Code262K
Kimi K2.5262K
Kimi K2 Thinking262K
Mistral Medium 3.5262K
Jamba Mini 1.7Rank 76 of 102256K
Can I run Jamba Mini 1.7 locally?
Yes, the weights are open.
Stated by AI21
- Open weights
- yes
- License
- Jamba Open Model License
- Parameters
- n/a
- active per token
- n/a
Sources and data date
Show all 15 sources
Benchmark sources at a glance
Which independent evaluators tested this model. This is coverage, not a quality ranking.
| Evaluator | Test series | Composite indices | Recorded active measurements |
|---|---|---|---|
| Artificial Analysis | 1 | 0 | 1 |
Without vendor claims and historical or disputed results; those stay labelled in the single values.
| Type | Evidence and data date |
|---|---|
| Research status | Research date October 4, 2026. 8 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication. |
| Unresolved | benchmark-model-identity Note Vectara names ai21labs/jamba-mini-1.7-2025-07. AI21 lists snapshot 2025-07 alongside API endpoint jamba-mini-1.7-2025-08. The conflicting dated model identities remain unresolved. |
| Not found in the inspected sources | benchmark-weights-revision Note The paper identifies the Hugging Face repository but does not bind the evaluation to a commit SHA or immutable weight revision. |
| Unresolved | dated-api-alias-identity Note This exact Hugging Face checkpoint score does not resolve the separate mismatch between Vectara's jamba-mini-1.7-2025-07 label and AI21's jamba-mini-1.7-2025-08 API endpoint. |
| Not published | exact-served-checkpoint-and-evaluation-configuration Note Kagi publishes the OpenRouter route name and aggregate accuracy, but not the exact served checkpoint, per-model sample count, confidence interval, reasoning setting, or result date. The route-level result does not settle the existing dated checkpoint/API identity mismatch. |
| Additional source | AI21 Jamba Mini 1.7 model card (retrieved October 16, 2026; October 25, 2026) · AI21 Jamba Mini 1.7 model card · Editorial description reviewed October 4, 2026 |
| Additional source | Artificial Analysis (retrieved November 2, 2026) |
| Additional source | Artificial Analysis (retrieved November 2, 2026; November 6, 2026) |
| Additional source | AI21 Jamba Mini 1.7 model card (retrieved October 4, 2026) |
| Additional source | Directed Attention is All You Need: Profiling Style from Limited Text Data (SIGTURK 2026) (retrieved October 16, 2026) |
| Additional source | Kagi LLM Benchmarking Project (retrieved October 17, 2026) |
| Additional source | Model metadata (retrieved October 4, 2026)123 |
| Additional source | OpenRouter: Popularity index (derived), CC BY 4.0 |
| Additional source | Vercel AI Gateway: Popularity index (derived), CC BY 4.0 |
| Additional source | Ollama: cumulative downloads for the popularity index |
| Additional source | Replicate: cumulative runs for the popularity index |
| Additional source | Google Trending Now: limited feed selection for Germany and the US |
| Additional source | Creative Commons Attribution 4.0 |