Skip to content
fedi.software

intellect-3 in fedi-index

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

fedi-index · General

C 1,328 ±5

Percentile 41 · #173 · provisional

People prefer / Solves tasks

1,337 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

C General 1,328 [1,324–1,333] Percentile 41 · #173 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,356 ±4.19 1,356 ±4 28.0% 2026-10-02 —
LMArena text/hard_prompts 1,352 ±5.68 1,351 ±5 27.0% 2026-10-02 —
LMArena text/instruction_following 1,316 ±7.90 1,334 ±8 12.1% 2026-10-02 —
LMArena text/expert 1,322 ±16 1,330 ±13 8.5% 2026-10-02 —
LMArena text/longer_query 1,332 ±8.27 1,337 ±8 5.9% 2026-10-02 —
LMArena text/multi_turn 1,349 ±10 1,353 ±9 5.4% 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

C Coding 1,340 [1,326–1,355] Percentile 40 · #168 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,375 ±9.31 1,359 ±8 88.0% 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 Math 1,336 [1,312–1,359] Percentile 41 · #150 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,374 ±15 1,368 ±15 80.1% 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 1,330 [1,317–1,344] Percentile 45 · #148 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,318 ±11 1,345 ±11 57.3% 2026-10-02 —
LMArena text/longer_query 1,332 ±8.27 1,337 ±8 34.5% 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 1,328 [1,309–1,346] Percentile 32 · #151 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,356 ±13 1,339 ±11 91.4% 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

C Language: English 1,355 [1,343–1,366] Percentile 47 · #145 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,379 ±6.06 1,366 ±6 93.1% 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 1,339 [1,319–1,359] Percentile 39 · #144 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,339 ±12 1,352 ±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

History

fedi-index by month
The same in a table
Model 2026-10
intellect-3 1,328 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: intellect-3

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