The AI arena is free today

Open Superagent

IBM Granite 4.0 Tiny Preview vs Jamba 1.5 Large

Jamba 1.5 Large leads the LLM Stats Score 0.9 to -5.5.

IBM · AI21 Labs · Updated for 2026

Which is better?

Jamba 1.5 Large leads the overall LLM Stats Score 0.9 to -5.5, ranking #325 overall.

In the 4 individual benchmarks reported for both models, Jamba 1.5 Large wins 4; this is a narrower head-to-head signal than the composite indexes.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose IBM Granite 4.0 Tiny Preview

  • you want the most recent training data — it shipped May 2025

Choose Jamba 1.5 Large

  • overall performance matters — it scores 0.9 and ranks #325 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 4 of 4 exact shared results

At a glance

The differences that matter most.

IBM Granite 4.0 Tiny Preview
IBM
Jamba 1.5 Large
AI21 Labs
Core performance indexes
LLM Stats Score
-5.5
#361
0.9
#325
Reasoning
-5.5
#351
1.0
#317
Cost, coverage & limits
Benchmark wins
0 of 4
4 of 4
Input price
— / M
$2.00 / M
Output price
— / M
$8.00 / M
Context window
—
256,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

3 shared
Index
IBM Granite 4.0 Tiny Preview
Jamba 1.5 Large
Math
-5.8#318
4.4#282
Finance
-3.7#208
5.3#170
Legal
-3.7#193
5.3#156
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

12 reported for IBM Granite 4.0 Tiny Preview · 8 for Jamba 1.5 Large

4 shared

IBM Granite 4.0 Tiny Preview outperforms in 0 benchmarks, while Jamba 1.5 Large is better at 4 benchmarks (Arena Hard, GSM8k, MMLU, TruthfulQA).

Jamba 1.5 Large significantly outperforms across most benchmarks.

Tue Sep 22 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

391.0B diff

Jamba 1.5 Large has 391.0B more parameters than IBM Granite 4.0 Tiny Preview, making it 5585.7% larger.

IBM
IBM Granite 4.0 Tiny Preview
7.0Bparameters
AI21 Labs
Jamba 1.5 Large
398.0Bparameters
7.0B
IBM Granite 4.0 Tiny Preview
398.0B
Jamba 1.5 Large

Context Window

Maximum input and output token capacity

Only Jamba 1.5 Large specifies input context (256,000 tokens). Only Jamba 1.5 Large specifies output context (256,000 tokens).

IBM
IBM Granite 4.0 Tiny Preview
Input- tokens
Output- tokens
AI21 Labs
Jamba 1.5 Large
Input256,000 tokens
Output256,000 tokens
Tue Sep 22 2026 • llm-stats.com

License

Usage and distribution terms

IBM Granite 4.0 Tiny Preview is licensed under Apache 2.0, while Jamba 1.5 Large uses Jamba Open Model License.

License differences may affect how you can use these models in commercial or open-source projects.

IBM Granite 4.0 Tiny Preview

Apache 2.0

Open weights

Jamba 1.5 Large

Jamba Open Model License

Open weights

Release Timeline

When each model was launched

IBM Granite 4.0 Tiny Preview was released on 2025-05-02, while Jamba 1.5 Large was released on 2024-08-22.

IBM Granite 4.0 Tiny Preview is 8 months newer than Jamba 1.5 Large.

IBM Granite 4.0 Tiny Preview

May 2, 2025

1.4 years ago

8mo newer
Jamba 1.5 Large

Aug 22, 2024

2.1 years ago

Knowledge Cutoff

When training data ends

Jamba 1.5 Large has a documented knowledge cutoff of 2024-03-05, while IBM Granite 4.0 Tiny Preview's cutoff date is not specified.

We can confirm Jamba 1.5 Large's training data extends to 2024-03-05, but cannot make a direct comparison without IBM Granite 4.0 Tiny Preview's cutoff date.

IBM Granite 4.0 Tiny Preview

—

Jamba 1.5 Large

Mar 2024

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Judge for yourself.

Run your own prompts against IBM Granite 4.0 Tiny Preview and Jamba 1.5 Large side-by-side, then vote on the output you prefer.

IBM Granite 4.0 Tiny Preview
✓ Preferred
Jamba 1.5 Large
Open in Playground

FAQ

Common questions about IBM Granite 4.0 Tiny Preview vs Jamba 1.5 Large.

Which is better, IBM Granite 4.0 Tiny Preview or Jamba 1.5 Large?

Jamba 1.5 Large leads the LLM Stats Score 0.9 to -5.5. IBM Granite 4.0 Tiny Preview is made by IBM and Jamba 1.5 Large is made by AI21 Labs. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does IBM Granite 4.0 Tiny Preview compare to Jamba 1.5 Large in benchmarks?

IBM Granite 4.0 Tiny Preview scores AttaQ: 86.1%, HumanEval: 82.4%, HumanEval+: 78.3%, GSM8k: 70.1%, IFEval: 63.0%. Jamba 1.5 Large scores ARC-C: 93.0%, GSM8k: 87.0%, MMLU: 81.2%, Arena Hard: 65.4%, TruthfulQA: 58.3%.

What are the context window sizes for IBM Granite 4.0 Tiny Preview and Jamba 1.5 Large?

IBM Granite 4.0 Tiny Preview supports an unknown number of tokens and Jamba 1.5 Large supports 256K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between IBM Granite 4.0 Tiny Preview and Jamba 1.5 Large?

Key differences include LLM Stats Score (-5.5 vs 0.9), licensing (Apache 2.0 vs Jamba Open Model License). See the full comparison above for benchmark-by-benchmark results.

Who makes IBM Granite 4.0 Tiny Preview and Jamba 1.5 Large?

IBM Granite 4.0 Tiny Preview is developed by IBM and Jamba 1.5 Large is developed by AI21 Labs.

Related comparisons