Kimi K2 0711 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
C 1,356 ±9
Percentile 49 · #150
People prefer / Solves tasks
1,363 / 1,346
Human votes vs benchmarks, Elo-eq
Value
-22
$1.00 per 1M tokens, median of 11 providers
On your hardware
Does not fit the reference setups.
Score decomposition
C General 1,356 [1,347–1,364] Percentile 49 · #150 · components: 7
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
140 ±1.39 | 1,360 ±11 | 39.0% | 2025-07-12 | — |
| LMArena |
text/overall
|
1,380 ±3.32 | 1,380 ±3 | 16.3% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,384 ±4.27 | 1,380 ±4 | 16.0% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,347 ±5.62 | 1,363 ±5 | 7.6% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,363 ±12 | 1,364 ±10 | 5.9% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,371 ±4.61 | 1,372 ±4 | 4.0% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,353 ±5.87 | 1,357 ±6 | 3.8% | 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
C Coding 1,361 [1,351–1,371] Percentile 48 · #144 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,399 ±6.34 | 1,380 ±6 | 89.4% | 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 Math 1,361 [1,344–1,378] Percentile 48 · #132 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,396 ±11 | 1,390 ±10 | 84.6% | 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
C Writing 1,357 [1,347–1,367] Percentile 50 · #135 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,349 ±7.79 | 1,376 ±8 | 59.3% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,353 ±5.87 | 1,357 ±6 | 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 1,373 [1,359–1,387] Percentile 46 · #122 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,416 ±9.83 | 1,386 ±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
C Language: English 1,355 [1,346–1,364] Percentile 47 · #144 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,379 ±4.50 | 1,366 ±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
C Language: Español 1,363 [1,338–1,389] Percentile 28 · #107 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,383 ±16 | 1,383 ±15 | 89.0% | 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 Language: 한국어 1,360 [1,336–1,384] Percentile 33 · #92 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,325 ±18 | 1,378 ±14 | 89.9% | 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 Language: Polski 1,373 [1,355–1,390] Percentile 28 · #94 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,377 ±12 | 1,388 ±10 | 91.8% | 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
C Language: Русский 1,378 [1,361–1,394] Percentile 49 · #120 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,384 ±10 | 1,393 ±9 | 92.1% | 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
History
The same in a table
| Model | 2026-10 |
|---|---|
| Kimi K2 0711 | 1,356 C |
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.