The AI arena is free today

Open Superagent

Jamba 1.5 Large vs Ministral 3 (3B Instruct 2512)

Jamba 1.5 Large and Ministral 3 (3B Instruct 2512) are closely matched at 0.9 and 2.2 on the LLM Stats Score.

AI21 Labs · Mistral AI · Updated for 2026

Which is better?

Jamba 1.5 Large and Ministral 3 (3B Instruct 2512) are closely matched on the overall LLM Stats Score at 0.9 and 2.2.

The models split the 2 individual benchmarks reported for both models evenly.

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

Choose Jamba 1.5 Large

  • you want predictable pricing at $2.00/M input and $8.00/M output

Choose Ministral 3 (3B Instruct 2512)

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

At a glance

The differences that matter most.

Jamba 1.5 Large
AI21 Labs
Ministral 3 (3B Instruct 2512)
Mistral AI
Core performance indexes
LLM Stats Score
0.9
#322
2.2
#316
Reasoning
1.0
#314
2.7
#305
Cost, coverage & limits
Benchmark wins
1 of 2
1 of 2
Input price
$2.00 / M
— / M
Output price
$8.00 / M
— / M
Context window
256,000
—

Individual benchmarks

8 reported for Jamba 1.5 Large · 4 for Ministral 3 (3B Instruct 2512)

2 shared

Jamba 1.5 Large outperforms in 1 benchmarks (Arena Hard), while Ministral 3 (3B Instruct 2512) is better at 1 benchmark (Wild Bench).

Both models are evenly matched across the benchmarks.

Mon Sep 21 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

395.0B diff

Jamba 1.5 Large has 395.0B more parameters than Ministral 3 (3B Instruct 2512), making it 13166.7% larger.

AI21 Labs
Jamba 1.5 Large
398.0Bparameters
Mistral AI
Ministral 3 (3B Instruct 2512)
3.0Bparameters
398.0B
Jamba 1.5 Large
3.0B
Ministral 3 (3B Instruct 2512)

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).

AI21 Labs
Jamba 1.5 Large
Input256,000 tokens
Output256,000 tokens
Mistral AI
Ministral 3 (3B Instruct 2512)
Input- tokens
Output- tokens
Mon Sep 21 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Ministral 3 (3B Instruct 2512) supports multimodal inputs, whereas Jamba 1.5 Large does not.

Ministral 3 (3B Instruct 2512) can handle both text and other forms of data like images, making it suitable for multimodal applications.

Jamba 1.5 Large

Text
Images
Audio
Video

Ministral 3 (3B Instruct 2512)

Text
Images
Audio
Video

License

Usage and distribution terms

Jamba 1.5 Large is licensed under Jamba Open Model License, while Ministral 3 (3B Instruct 2512) uses Apache 2.0.

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

Jamba 1.5 Large

Jamba Open Model License

Open weights

Ministral 3 (3B Instruct 2512)

Apache 2.0

Open weights

Release Timeline

When each model was launched

Jamba 1.5 Large was released on 2024-08-22, while Ministral 3 (3B Instruct 2512) was released on 2025-12-04.

Ministral 3 (3B Instruct 2512) is 16 months newer than Jamba 1.5 Large.

Jamba 1.5 Large

Aug 22, 2024

2.1 years ago

Ministral 3 (3B Instruct 2512)

Dec 4, 2025

9 months ago

1.3yr newer

Knowledge Cutoff

When training data ends

Jamba 1.5 Large has a documented knowledge cutoff of 2024-03-05, while Ministral 3 (3B Instruct 2512)'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 Ministral 3 (3B Instruct 2512)'s cutoff date.

Jamba 1.5 Large

Mar 2024

Ministral 3 (3B Instruct 2512)

—

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Judge for yourself.

Run your own prompts against Jamba 1.5 Large and Ministral 3 (3B Instruct 2512) side-by-side, then vote on the output you prefer.

Jamba 1.5 Large
✓ Preferred
Ministral 3 (3B Instruct 2512)
Open in Playground

FAQ

Common questions about Jamba 1.5 Large vs Ministral 3 (3B Instruct 2512).

Which is better, Jamba 1.5 Large or Ministral 3 (3B Instruct 2512)?

Jamba 1.5 Large and Ministral 3 (3B Instruct 2512) are closely matched on the LLM Stats Score at 0.9 and 2.2. Jamba 1.5 Large is made by AI21 Labs and Ministral 3 (3B Instruct 2512) is made by Mistral AI. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Jamba 1.5 Large compare to Ministral 3 (3B Instruct 2512) in benchmarks?

Jamba 1.5 Large scores ARC-C: 93.0%, GSM8k: 87.0%, MMLU: 81.2%, Arena Hard: 65.4%, TruthfulQA: 58.3%. Ministral 3 (3B Instruct 2512) scores MATH: 83.0%, Wild Bench: 56.8%, Arena Hard: 30.5%, MM-MT-Bench: 7.8%.

What are the context window sizes for Jamba 1.5 Large and Ministral 3 (3B Instruct 2512)?

Jamba 1.5 Large supports 256K tokens and Ministral 3 (3B Instruct 2512) supports an unknown number of tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Jamba 1.5 Large and Ministral 3 (3B Instruct 2512)?

Key differences include LLM Stats Score (0.9 vs 2.2), multimodal support (no vs yes), licensing (Jamba Open Model License vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes Jamba 1.5 Large and Ministral 3 (3B Instruct 2512)?

Jamba 1.5 Large is developed by AI21 Labs and Ministral 3 (3B Instruct 2512) is developed by Mistral AI.

Related comparisons