Skip to content
fedi.software

ling-flash-2.0 in fedi-index

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

fedi-index · General

C 1,334 ±4

Percentile 44 · #164 · provisional

People prefer / Solves tasks

1,343 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

C General 1,334 [1,330–1,338] Percentile 44 · #164 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,361 ±3.69 1,362 ±4 27.7% 2026-10-02 —
LMArena text/hard_prompts 1,363 ±5.05 1,362 ±5 26.9% 2026-10-02 —
LMArena text/instruction_following 1,318 ±6.91 1,336 ±6 12.3% 2026-10-02 —
LMArena text/expert 1,359 ±15 1,361 ±12 8.7% 2026-10-02 —
LMArena text/longer_query 1,325 ±8.18 1,331 ±8 5.8% 2026-10-02 —
LMArena text/multi_turn 1,323 ±8.94 1,329 ±8 5.7% 2026-10-02 —

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 Coding 1,353 [1,341–1,364] Percentile 46 · #150 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,389 ±7.45 1,372 ±7 88.9% 2026-10-02 —

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 Math 1,332 [1,311–1,353] Percentile 41 · #152 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,366 ±14 1,361 ±13 82.0% 2026-10-02 —

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 Writing 1,309 [1,296–1,322] Percentile 39 · #163 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,286 ±10 1,312 ±11 57.6% 2026-10-02 —
LMArena text/longer_query 1,325 ±8.18 1,331 ±8 34.3% 2026-10-02 —

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: 繁體中文 1,372 [1,352–1,392] Percentile 45 · #123 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,419 ±14 1,389 ±11 91.2% 2026-10-02 —

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 1,362 [1,352–1,372] Percentile 51 · #134 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,386 ±5.32 1,373 ±6 93.4% 2026-10-02 —

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

D Language: Polski 1,319 [1,294–1,344] Percentile 8 · #120 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/polish 1,312 ±17 1,333 ±14 89.3% 2026-10-02 —

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 1,314 [1,293–1,336] Percentile 32 · #159 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,310 ±13 1,326 ±12 90.7% 2026-10-02 —

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 2026-10
ling-flash-2.0 1,334 C

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: ling-flash-2.0

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