Kimi K2.6 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
A 1,435 ±5
Percentile 84 · #48
People prefer / Solves tasks
1,443 / 1,423
Human votes vs benchmarks, Elo-eq
Value
+44
$1.71 per 1M tokens, median of 56 providers · vendor $1.71
On your hardware
Does not fit the reference setups.
Score decomposition
A General 1,435 [1,430–1,440] Percentile 84 · #48 · components: 9
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
151 ±0.90 | 1,446 ±7 | 34.1% | 2026-04-20 | — |
| LMArena |
text/overall
|
1,455 ±2.25 | 1,456 ±2 | 15.6% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,470 ±2.63 | 1,458 ±2 | 15.5% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,451 ±3.22 | 1,461 ±3 | 7.6% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,491 ±5.06 | 1,469 ±4 | 7.4% | 2026-10-02 | — |
| Epoch AI |
simpleqa_verified
decay ×0.61 |
0.35 ±0.02 | 1,407 ±5 | 3.8% | 2026-08-10 | — |
| LMArena |
text/longer_query
|
1,468 ±3.08 | 1,464 ±3 | 3.8% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,453 ±4.05 | 1,447 ±4 | 3.8% | 2026-10-02 | — |
| Epoch AI |
gpqa_diamond
decay ×0.26 |
0.91 ±0.02 | 1,462 ±8 | 1.4% | 2026-05-01 | — |
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
A Coding 1,436 [1,433–1,440] Percentile 87 · #36 · components: 3
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
webdev/overall
|
1,509 ±3.68 | 1,452 ±1 | 39.7% | 2026-10-01 | — |
| LMArena |
text/coding
|
1,489 ±3.49 | 1,460 ±3 | 38.2% | 2026-10-02 | — |
| Epoch AI |
swe_bench_verified
decay ×0.37 |
0.77 ±0.02 | 1,466 ±10 | 13.7% | 2026-05-08 | — |
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
A Math 1,436 [1,428–1,444] Percentile 87 · #33 · components: 3
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,475 ±6.67 | 1,465 ±6 | 51.5% | 2026-10-02 | — |
| Epoch AI |
frontiermath_t1_3
decay ×0.86 |
0.57 ±0.03 | 1,445 ±6 | 29.7% | 2026-06-10 | — |
| Epoch AI |
frontiermath_t4
decay ×0.86 |
0.26 ±0.07 | 1,434 ±11 | 11.2% | 2026-06-10 | — |
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 Vision 1,444 [1,440–1,448] Percentile 79 · #25 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,282 ±3.47 | 1,459 ±3 | 63.1% | 2026-10-02 | — |
| LMArena |
vision/ocr
|
1,292 ±3.62 | 1,463 ±4 | 15.6% | 2026-10-02 | — |
| LMArena |
vision/diagram
|
1,299 ±5.20 | 1,462 ±5 | 15.0% | 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
A Writing 1,448 [1,442–1,453] Percentile 85 · #42 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,434 ±4.19 | 1,464 ±4 | 61.6% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,468 ±3.08 | 1,464 ±3 | 32.1% | 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
A Language: 繁體中文 1,452 [1,442–1,461] Percentile 90 · #24 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,520 ±6.53 | 1,469 ±5 | 93.5% | 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
B Language: Deutsch 1,425 [1,408–1,442] Percentile 75 · #37 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,449 ±11 | 1,444 ±9 | 92.0% | 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
A Language: English 1,436 [1,431–1,442] Percentile 86 · #38 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,460 ±2.86 | 1,452 ±3 | 93.9% | 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
A Language: Español 1,439 [1,425–1,453] Percentile 82 · #28 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,464 ±8.49 | 1,458 ±8 | 92.6% | 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
B Language: Français 1,434 [1,420–1,448] Percentile 75 · #35 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,471 ±8.37 | 1,452 ±8 | 92.7% | 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
A Language: 日本語 1,436 [1,417–1,455] Percentile 82 · #24 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,442 ±14 | 1,458 ±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
A Language: 한국어 1,437 [1,421–1,453] Percentile 83 · #24 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,429 ±12 | 1,457 ±9 | 92.2% | 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: Polski 1,421 [1,405–1,438] Percentile 66 · #45 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,438 ±11 | 1,440 ±9 | 92.2% | 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: Русский 1,433 [1,425–1,441] Percentile 80 · #48 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,446 ±4.77 | 1,448 ±4 | 93.7% | 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
The same in a table
| Model | 2026-10 |
|---|---|
| Kimi K2.6 | 1,435 A |
Badge
Show the model's fedi-index on your site or in a README. The badge updates itself; it links to this page.
Data CC BY 4.0: keep the link to fedi.software.