Decision support

Beam 1.0 501B A23B vs Ripple-65B Preview

Compare canonical objects directly. The useful dimensions change with the object type, so model and hardware comparisons stay separate.

Models Hardware

Beam 1.0 501B A23B

Reflection AI

Sources:models.devOpenRouter

Ripple-65B Preview

Ricursive Intelligence

Sources:OpenRouter

Benchmark results

Arena Text
Arena rating · Higher is better
- Beam 1.0 501B A23B
  1435
  Arena #108CI 1425 to 1444
- Ripple-65B Preview
  Not reported
Runs and sources
Beam 1.0 501B A23B
default143595% CI 1425 to 1444 · 4,006 votes
Ripple-65B Preview
Not reported
Source:Arena Text leaderboard, 2026-11-09
Arena WebDev
Arena rating · Higher is better
- Beam 1.0 501B A23B
  1437
  Arena #89CI 1423 to 1450
- Ripple-65B Preview
  Not reported
Runs and sources
Beam 1.0 501B A23B
default143795% CI 1423 to 1450 · 2,515 votes
Ripple-65B Preview
Not reported
Source:Arena WebDev leaderboard, 2026-11-10
Agent Arena
IPS score · Higher is better
- Beam 1.0 501B A23B
  -0.059
  Arena #45CI -0.085 to -0.033
- Ripple-65B Preview
  Not reported
Runs and sources
Beam 1.0 501B A23B
default-0.05995% CI -0.085 to -0.033 · 696,272 observations
Ripple-65B Preview
Not reported
Source:Agent Arena leaderboard, 2026-11-11

Each model's best published result is shown; "Not reported" means no matched evaluation, not a score of zero. Arena and DeepSWE ranks are the leaderboards' own; other ranks are among catalogue models with a score. Results from different harnesses or settings are not directly comparable.

Arena ratings: Arena (lmarena-ai/leaderboard-dataset), licensed CC BY 4.0. Ratings come from pairwise human votes and are only comparable within one leaderboard; the interval is Arena's 95% confidence interval. Model names are matched to the Vertical Tabs catalog.

Model specifications

Release date

October 16, 2026

November 4, 2026

Context window

Native context

—

Max output tokens

943,718

131,072

Knowledge cutoff

2026-06-30

—

Open weights

Parameter count

501B

65B

API pricing · USD per 1M tokens

Input

$0.30

$0.20

Output

$1.00

$0.60

Cached input

$0.04

$0.05

Cache write

—

Capabilities and modalities

Input modalities

text

Output modalities

text

Tool calling

Supported

Reasoning option

Supported

Supported options

frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p

frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p

Capabilities

—

Architecture and availability

Architecture

—

Model families

—

Tokenizer

Other

Instruction format

—

License

Apache-2.0

Apache 2.0

Providers

Provider endpoints

Ollama variants

Metadata source

ai-research

curated

A dash means the field is not reported. Provider-specific performance and pricing may differ.

Benchmark results

Arena Text

Arena WebDev

Agent Arena

Model specifications

API pricing · USD per 1M tokens

Capabilities and modalities

Architecture and availability