Skip to content
fedi.software

Nova 2 Lite in fedi-index

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

fedi-index · General

C 1,338 ±3

Percentile 44 · #163 · provisional

People prefer / Solves tasks

1,347 / —

Human votes vs benchmarks, Elo-eq

Value

-36

$0.85 per 1M tokens, median of 3 providers

On your hardware

Closed weights: cloud only.

Score decomposition

C General 1,338 [1,335–1,342] Percentile 44 · #163 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,362 ±3.07 1,362 ±3 26.6% 2026-10-02 —
LMArena text/hard_prompts 1,364 ±3.96 1,362 ±4 26.2% 2026-10-02 —
LMArena text/instruction_following 1,334 ±5.18 1,351 ±5 12.5% 2026-10-02 —
LMArena text/expert 1,358 ±11 1,360 ±9 10.4% 2026-10-02 —
LMArena text/longer_query 1,335 ±5.44 1,339 ±5 6.2% 2026-10-02 —
LMArena text/multi_turn 1,338 ±6.70 1,342 ±6 5.9% 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 Coding 1,351 [1,342–1,360] Percentile 45 · #153 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,386 ±5.88 1,368 ±5 89.5% 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 Math 1,332 [1,316–1,348] Percentile 40 · #153 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,359 ±10 1,354 ±10 85.0% 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 1,316 [1,307–1,326] Percentile 42 · #157 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,291 ±7.38 1,317 ±8 59.5% 2026-10-02 —
LMArena text/longer_query 1,335 ±5.44 1,339 ±5 33.5% 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 1,335 [1,322–1,348] Percentile 35 · #145 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,364 ±9.15 1,345 ±7 92.8% 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 1,361 [1,352–1,369] Percentile 50 · #137 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,384 ±4.35 1,372 ±5 93.6% 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 1,331 [1,308–1,354] Percentile 12 · #115 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/polish 1,326 ±15 1,345 ±13 90.3% 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 1,344 [1,332–1,357] Percentile 40 · #141 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,342 ±7.68 1,355 ±7 93.0% 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

History

fedi-index by month
The same in a table
Model 2026-10
Nova 2 Lite 1,338 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: Nova 2 Lite

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