Skip to content
fedi.software

Beam 1.0 501B A23B in fedi-index

The score in every slice, what it is made of, value, local run and history.

fedi-index · General

B 1,400 ±5

Percentile 66 · #103 · provisional

People prefer / Solves tasks

1,414 / —

Human votes vs benchmarks, Elo-eq

Value

+42

$0.60 per 1M tokens, median of 10 providers

On your hardware

  • 128 GB unified memory #38 · UD-IQ1_S · strong compression · ≈26 tok/s

Score decomposition

B General 1,400 [1,395–1,405] Percentile 66 · #103 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,424 ±4.90 1,424 ±5 27.5% 2026-11-11 —
LMArena text/hard_prompts 1,442 ±6.14 1,433 ±6 26.8% 2026-11-11 —
LMArena text/instruction_following 1,424 ±8.08 1,436 ±8 12.1% 2026-11-11 —
LMArena text/expert 1,464 ±15 1,446 ±12 9.0% 2026-11-11 —
LMArena text/longer_query 1,428 ±7.54 1,426 ±7 6.2% 2026-11-11 —
LMArena text/multi_turn 1,421 ±12 1,418 ±11 5.0% 2026-11-11 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

B Coding 1,409 [1,402–1,416] Percentile 69 · #89 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena webdev/overall 1,436 ±6.98 1,432 ±2 49.4% 2026-11-15 —
LMArena text/coding 1,475 ±9.56 1,448 ±8 38.0% 2026-11-11 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

C Agents 1,391 [1,380–1,403] Percentile 31 · #54 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena agent/overall -0.07 ±0.01 1,420 ±7 86.8% 2026-11-15 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

B Writing 1,403 [1,390–1,416] Percentile 64 · #95 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,388 ±11 1,416 ±11 56.7% 2026-11-11 —
LMArena text/longer_query 1,428 ±7.54 1,426 ±7 35.2% 2026-11-11 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

B Language: English 1,408 [1,393–1,423] Percentile 66 · #93 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,435 ±7.87 1,425 ±8 92.4% 2026-11-11 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

B Language: Русский 1,393 [1,372–1,413] Percentile 55 · #104 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,405 ±13 1,411 ±11 91.1% 2026-11-11 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

History

fedi-index by month
The same in a table
Model 2026-11
Beam 1.0 501B A23B 1,400 B

Badge

Show the model's fedi-index on your site or in a README. The badge updates itself; it links to this page.

fedi-index: Beam 1.0 501B A23B

Data CC BY 4.0: keep the link to fedi.software.