Advertise here
#266

Beam 1.0 501B A23B

Reflection Release: 2026-10-17 Tested on: 2026-10-17 10:59 reflection/beam-1.0-501b-a23b::high
501B total (23B active)MoEOpen source

Summary

Beam 1.0 501B A23B scores 6.1 on AI BENCHY and ranks #266. It has 10.0 reliability, a 59.4% pass rate, $0.674 total cost, and 9.03s average response time.

What makes Beam 1.0 501B A23B unique: It stands out most in Coding, where it ranks #2, while Tool Calling is its weakest area at #13.

Model facts

Researched on 2026-10-17

Reported
Parameters
501B total (23B active)
Architecture
MoE
Availability
Open source
License
Apache-2.0

The official model card reports 501B total and 23B active parameters, Apache-2.0 weights and public inference integrations. Text-only reasoning model for coding, tool use and mathematical/scientific work. OpenRouter declares mandatory reasoning with low, medium, high, xhigh and max efforts. All four current provider endpoints publish training=false. Provider rates differ; the catalog currently quotes CoreWeave at $1/$3 per million, while eligible Nebius starts at $0.25/$1. Fallback release date records this onboarding request date.

Score

6.1

Consistency

8.3

Total Output Tokens

147,207

Total Input Tokens

232,218

Input Price

$1.000 / 1M

Output Price

$3.000 / 1M

Cache Read Price

$0.100 / 1M

Cache Write Price

N/A

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Tests Correct

Wrong Tests: 12

Attempt pass rate: 59.4%

Flaky tests

5

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

9.03s

Response Time (max): 36.04s

Response Time (total): 207.67s

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#266 Beam 1.0 501B A23B

high
Cost
$0.008
Time
15.6s
Tokens
6,162 tok

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Category Breakdown

Category Score Consistency Tests Correct
Agentic 3.0 10.0
Anti-AI Tricks 8.8 8.3
Coding 8.4 7.4
Combined 3.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 3.6 7.2
General Intelligence 5.1 3.4
Instructions following 9.8 10.0
Puzzle Solving 8.2 7.2
Tool Calling 3.0 10.0
Trivia 3.0 10.0

Compared models