Skip to content
fedi.software

Kimi K2.7 Code in fedi-index

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

fedi-index · General

B 1,400 ±11

Percentile 68 · #94 · provisional

People prefer / Solves tasks

— / 1,416

Human votes vs benchmarks, Elo-eq

Value

+9

$1.71 per 1M tokens, median of 47 providers · vendor $1.71

On your hardware

Does not fit the reference setups.

Score decomposition

B General 1,400 [1,390–1,411] Percentile 68 · #94 · components: 3 provisional
Source Component Value Elo-eq Weight Measured Variant
Epoch AI eci 150 ±0.92 1,438 ±7 73.8% 2026-06-12 —
Epoch AI simpleqa_verified decay ×0.61 0.36 ±0.02 1,412 ±5 8.4% 2026-08-27 —
Epoch AI gpqa_diamond decay ×0.26 0.88 ±0.02 1,448 ±11 2.6% 2026-08-07 —

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 1,419 [1,417–1,422] Percentile 77 · #65 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena webdev/overall 1,473 ±4.78 1,442 ±1 90.5% 2026-10-01 —

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 Math 1,396 [1,387–1,404] Percentile 68 · #82 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
Epoch AI frontiermath_t1_3 decay ×0.86 0.54 ±0.03 1,438 ±6 58.5% 2026-06-13 —
Epoch AI frontiermath_t4 decay ×0.86 0.12 ±0.05 1,412 ±8 26.5% 2026-06-13 —

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
Kimi K2.7 Code 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: Kimi K2.7 Code

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