Inference
EN

Beam 1.0

Beam 1.0 is a model. 9 benchmarks count toward its index, in 4 categories.

  • Input: text
RankedEnough results for an index.
IndexAll categories, out of 100.58.8±8.9Median 51.0
CoverageIndex weight that has results.65%
SpeedOutput tokens per second.—Median 67/s
First tokenSeconds to the first output token.—Median 1.3 s
Input / 1MUS dollars per 1M input tokens.—Median $0.60
Output / 1MUS dollars per 1M output tokens.—Median $2.55
ContextMaximum tokens in one request.—Median 262K
EloLMArena rating and rank.—Median 1422

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.2 counted62.358 / 218
CodingCode writing and repair.3 counted63.352 / 209
ReasoningLogic problems and puzzles.3 counted55.880 / 227
MultimodalTasks with images and text.None counted——
KnowledgeFacts and expert knowledge.None counted——
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.None counted——
MathMath problems.1 counted53.4—

Results

9 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
Vibe Code Bench v1.1Coding66.4% ±4.153 / 123
ARC-AGI-2 (semi-private)Reasoning23.5%58 / 131
ARC-AGI-1 (semi-private)Reasoning74.0%57 / 126
LiveBench Coding 2.0Coding83.9%26 / 52
LiveBench ResearchAgentic72.8%27 / 52
LiveBench ReasoningReasoning80.2%56 / 80
LiveBench DesignAgentic67.9%40 / 52
LiveBench Data AnalysisReasoning66.4%62 / 80
ProofBench v1.1Math18.0% ±3.944 / 54
LiveBench Long AgenticAgentic17.3%43 / 51
Terminal-Bench 4.0Agentic4.0% ±1.352 / 61
IOICoding22.8% ±8.041 / 45
ARC-AGI-2 (public eval)Reasoning26.3%50 / 122
ARC-AGI-1 (public eval)Reasoning79.1%52 / 116
Legal Research BenchLegal28.8% ±3.157 / 90
MysteryMechanismScience22.1% ±2.822 / 30
HLAB-Vals-1.1Legal4.6% ±1.829 / 35
Terminal-Bench-ScienceScience1.4% ±1.437 / 44
Tax Agent BenchFinance8.8% ±1.969 / 82
BioMysteryBenchScience42.6% ±1.630 / 30

Sources

BenchLMCC BY-NC 4.0LiveBenchNo licence statedARC Prize FoundationTerms restrict reuseVals AINo licence stated

History

5 releases
Index59.1 → 58.8
29 Oct 202612 Nov 2026

Questions

How good is Beam 1.0?
Its index is 58.8 out of 100. That is place 81 of 283 ranked models.
What is Beam 1.0 best at?
Coding: 63.3 out of 100, place 52 of 209.

Badge

Beam 1.0 on Inference360: place 81 of 283, index 58.8
HTML
<a href="https://inference360.ai/models/unknown-beam-1-0"><img src="https://inference360.ai/badges/unknown-beam-1-0.svg" alt="Beam 1.0 on Inference360: place 81 of 283, index 58.8" height="20"></a>
Markdown
[![Beam 1.0 on Inference360: place 81 of 283, index 58.8](https://inference360.ai/badges/unknown-beam-1-0.svg)](https://inference360.ai/models/unknown-beam-1-0)

Compare with

GPT-5.259.0Kimi K2.658.2