Beam 1.0

Name: Beam 1.0
Author: Reflection

Reflection Released October 2026

Visit Reflection Full benchmarks

#72 smartest of 89 #4 fastest Updated Oct 31, 2026, 06:59 PM UTC

At a glance

How Beam 1.0 compares with the other 88 ranked language models.

Better for simple tasks. Ranked #72 of 89 on the overall intelligence score, ahead of 19% of models.
Fast writer. Writes about 255 words per second, faster than 97% of models.
Short wait before answering. You wait about 6.4 sec before the answer starts.
Cheap to use. $0.60 per million tokens, cheaper than 71% of models.

Model details

Made by: Reflection
Model family: Beam 1.0
Released: October 2026 · 2 weeks ago
Input price: $0.40 / 1M tokens
Output price: $1.20 / 1M tokens
Value for money: #22 of 84
Tests with scores: 4 of 8

Good for

Fast, live repliesWrites about 255 words per second

Not ideal for

Complex reasoningScores in the bottom quarter overall
Autonomous agentsWeak on multi-step computer tasks

Intelligence

overall score

#72 of 89typical 30

Coding

–

coding score

typical –

Speed

340

tokens per second

#4 of 89typical 91

Wait

6.4 sec

before it replies

#22 of 79typical 16s

Price

$0.60

per 1M tokens

#25 of 84typical $2.00

Test results

Scores on individual tests that make up the intelligence score. The faint line marks the best score of any model.

Humanity's Last Exam
Very hard expert questions across many subjects
35%#60 of 86typical 42%
SciCode
Writing code to solve science research problems
49%#65 of 86typical 53%
Long documents
Finding and reasoning over facts in very long texts
78%#62 of 87typical 80%
Terminal-Bench
Doing real tasks on a computer by itself, like an agent
3%#71 of 89typical 31%

Where it ranks on intelligence

This model next to the models closest to it. Click another bar to open that model.

What would it cost?

Through the API, at the listed price. Chat apps usually charge a monthly plan instead.

1,000 chat replies
a question and a ~350-word answer, 1,000 times
$1.00
Summarise a 100-page report
about 50,000 words in, a one-page summary out
$0.03
Write a 2,000-word article
a short brief in, a long article out
$0.004

Input, per 1M tokens

$0.40

Output, per 1M tokens

$1.20

How long do answers take?

Median times measured through the API.

Before the answer starts6.4 sec

Writing speed≈ 255 words / sec

A full 500-word answer8.3 sec

1 token is about ¾ of a word. Speeds change with server load, so treat these as typical, not guaranteed.

Similar models

Other companies' models with the closest intelligence score.

Questions people ask

Is Beam 1.0 a good AI model?

On the overall intelligence score it ranks #72 of 89 (score 18; the typical model scores 30). It stands out for fast, live replies.

How much does Beam 1.0 cost?

Through the API it costs $0.40 per million input tokens and $1.20 per million output tokens. In everyday terms, 1,000 chat replies cost about $1.00. Chat apps that use it usually charge a monthly plan instead.

How fast is Beam 1.0?

It writes about 255 words per second, and you wait about 6.4 sec before the answer starts. A full 500-word answer takes roughly 8.3 sec.

What are good alternatives to Beam 1.0?

Models with a similar score include K2 Horizon 375B A23B by Institute of Foundation Models, Kimi K3 by Kimi, MiniMax-M3 by MiniMax. The cheapest of these is Nemotron 3.5 Super VL at $0.28 per million tokens.

Benchmark data from Artificial Analysis, an independent benchmarking company. Rankings refresh every few hours.