Beam 1.0 vs Jamba 1.5 Large
Beam 1.0 leads the LLM Stats Score 44.6 to 0.5. Beam 1.0 is 5.8x cheaper per token.
Reflection AI · AI21 Labs · Updated for 2026
Which is better?
Beam 1.0 leads the overall LLM Stats Score 44.6 to 0.5, ranking #46 overall.
In the 1 individual benchmarks reported for both models, Beam 1.0 wins 1; this is a narrower head-to-head signal than the composite indexes.
On price, Beam 1.0 is roughly 5.8x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.
Beam 1.0 also accepts a larger context window (1,048,576 input tokens), making it the stronger choice for long documents and large codebases.
Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.
Choose Beam 1.0
- overall performance matters — it scores 44.6 and ranks #46 on LLM Stats
- your work emphasizes reasoning — it leads those capability indexes
- you value its reported benchmark strengths — it wins 1 of 1 exact shared results
- cost matters — it's about 5.8x cheaper per token
- you process long inputs — it offers a 1,048,576 token context window
- you want the most recent training data — it shipped Oct 2026
Choose Jamba 1.5 Large
- you want predictable pricing at $2.00/M input and $8.00/M output
At a glance
The differences that matter most.
Capability indexes
Additional strengths measured across groups of related public benchmarks
Individual benchmarks
22 reported for Beam 1.0 · 8 for Jamba 1.5 Large
Beam 1.0 outperforms in 1 benchmarks (GPQA), while Jamba 1.5 Large is better at 0 benchmarks.
Beam 1.0 significantly outperforms across most benchmarks.
Human preference
Blind head-to-head votes and playground preference scores
Pricing Analysis
Price comparison per million tokens
For input processing, Beam 1.0 ($0.40/1M tokens) is 5.0x cheaper than Jamba 1.5 Large ($2.00/1M tokens).
For output processing, Beam 1.0 ($1.20/1M tokens) is 6.7x cheaper than Jamba 1.5 Large ($8.00/1M tokens).
In conclusion, Jamba 1.5 Large is more expensive than Beam 1.0.*
* Using a 3:1 ratio of input to output tokens
Model Size
Parameter count comparison
Beam 1.0 has 103.3B more parameters than Jamba 1.5 Large, making it 26.0% larger.
Context Window
Maximum input and output token capacity
Beam 1.0 accepts 1,048,576 input tokens compared to Jamba 1.5 Large's 256,000 tokens. Jamba 1.5 Large can generate longer responses up to 256,000 tokens, while Beam 1.0 is limited to 131,072 tokens.
License
Usage and distribution terms
Beam 1.0 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.
Apache 2.0
Open weights
Jamba Open Model License
Open weights
Release Timeline
When each model was launched
Beam 1.0 was released on 2026-10-16, while Jamba 1.5 Large was released on 2024-08-22.
Beam 1.0 is 26 months newer than Jamba 1.5 Large.
Oct 16, 2026
4 days ago
2.2yr newerAug 22, 2024
2.2 years ago
Knowledge Cutoff
When training data ends
Beam 1.0 has a knowledge cutoff of 2026-06-30, while Jamba 1.5 Large has a cutoff of 2024-03-05.
Beam 1.0 has more recent training data (up to 2026-06-30), making it potentially better informed about events through that date compared to Jamba 1.5 Large (2024-03-05).
Jun 2026
2.3 yr newerMar 2024
Provider Availability
Beam 1.0 is available from Together, Reflection AI. Jamba 1.5 Large is available from Bedrock, Google.
Beam 1.0
Jamba 1.5 Large
Outputs Comparison
Judge for yourself.
Run your own prompts against Beam 1.0 and Jamba 1.5 Large side-by-side, then vote on the output you prefer.
FAQ
Common questions about Beam 1.0 vs Jamba 1.5 Large.