Skip to content
fedi.software

Inkling 2 Small in fedi-index

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

fedi-index · General

B 1,381 ±6

Percentile 57 · #127 · provisional

People prefer / Solves tasks

1,394 / —

Human votes vs benchmarks, Elo-eq

Value

+30

$0.475 per 1M tokens, median of 9 providers

On your hardware

Does not fit the reference setups.

Score decomposition

B General 1,381 [1,375–1,387] Percentile 57 · #127 · components: 5 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,403 ±5.98 1,403 ±6 31.4% 2026-11-11 —
LMArena text/hard_prompts 1,421 ±7.54 1,414 ±7 30.2% 2026-11-11 —
LMArena text/instruction_following 1,408 ±10 1,420 ±10 13.0% 2026-11-11 —
LMArena text/longer_query 1,403 ±9.40 1,403 ±9 6.8% 2026-11-11 —
LMArena text/multi_turn 1,408 ±15 1,406 ±13 5.1% 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

B Coding 1,411 [1,401–1,421] Percentile 70 · #88 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,455 ±12 1,430 ±11 47.5% 2026-11-11 —
LMArena webdev/overall outlier 1,645 ±9.50 1,491 ±3 34.6% 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 Agents 1,437 [1,432–1,442] Percentile 69 · #25 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena agent/overall 0.03 ±0.01 1,468 ±3 88.5% 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 1,370 [1,355–1,385] Percentile 53 · #124 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,348 ±12 1,375 ±13 55.6% 2026-11-11 —
LMArena text/longer_query 1,403 ±9.40 1,403 ±9 35.5% 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 1,389 [1,370–1,409] Percentile 57 · #116 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,418 ±10 1,407 ±11 91.4% 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

C Language: Русский 1,369 [1,346–1,391] Percentile 44 · #130 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,377 ±14 1,386 ±13 90.4% 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

History

fedi-index by month
The same in a table
Model 2026-11
Inkling 2 Small 1,381 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: Inkling 2 Small

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