Inkling in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
B 1,418 ±6
Percentile 78 · #65
People prefer / Solves tasks
1,426 / 1,407
Human votes vs benchmarks, Elo-eq
Value
+26
$1.76 per 1M tokens, median of 20 providers · vendor $2.57
On your hardware
Does not fit the reference setups.
Score decomposition
B General 1,418 [1,412–1,424] Percentile 78 · #65 · components: 9
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
149 ±1.20 | 1,426 ±9 | 31.2% | 2026-07-15 | — |
| LMArena |
text/overall
|
1,442 ±2.29 | 1,442 ±2 | 16.2% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,451 ±2.65 | 1,441 ±2 | 16.2% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,426 ±3.22 | 1,438 ±3 | 8.0% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,467 ±4.89 | 1,449 ±4 | 7.8% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,434 ±3.03 | 1,432 ±3 | 4.0% | 2026-10-02 | — |
| Epoch AI |
simpleqa_verified
decay ×0.61 |
0.40 ±0.02 | 1,424 ±5 | 4.0% | 2026-08-27 | xhigh |
| LMArena |
text/multi_turn
|
1,436 ±4.38 | 1,431 ±4 | 3.9% | 2026-10-02 | — |
| Epoch AI |
gpqa_diamond
decay ×0.26 |
0.88 ±0.02 | 1,450 ±9 | 1.4% | 2026-08-05 | xhigh |
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 1,409 [1,407–1,412] Percentile 73 · #75 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
webdev/overall
|
1,413 ±3.27 | 1,425 ±1 | 46.1% | 2026-10-01 | — |
| LMArena |
text/coding
|
1,464 ±3.51 | 1,438 ±3 | 44.3% | 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
D Agents 1,384 [1,380–1,389] Percentile 4 · #56 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
agent/overall
|
-0.11 ±0.01 | 1,404 ±2 | 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
A Math 1,416 [1,408–1,424] Percentile 81 · #49 · components: 3
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,478 ±7.55 | 1,468 ±7 | 48.1% | 2026-10-02 | — |
| Epoch AI |
frontiermath_t1_3
decay ×0.86 |
0.33 ±0.03 | 1,393 ±6 | 29.4% | 2026-08-06 | xhigh |
| Epoch AI |
frontiermath_t4
decay ×0.86 |
0.05 ±0.03 | 1,400 ±5 | 15.1% | 2026-08-06 | xhigh |
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 Writing 1,407 [1,401–1,412] Percentile 67 · #89 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,386 ±4.05 | 1,414 ±4 | 61.7% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,434 ±3.03 | 1,432 ±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
B Language: 繁體中文 1,431 [1,422–1,439] Percentile 78 · #50 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,491 ±5.99 | 1,446 ±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
B Language: Deutsch 1,420 [1,400–1,440] Percentile 70 · #44 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,445 ±13 | 1,441 ±11 | 91.1% | 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
B Language: English 1,419 [1,413–1,425] Percentile 73 · #74 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,443 ±3.04 | 1,433 ±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
B Language: Español 1,422 [1,406–1,438] Percentile 67 · #50 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,445 ±9.64 | 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: Français 1,419 [1,402–1,435] Percentile 60 · #54 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,455 ±9.92 | 1,437 ±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
B Language: 日本語 1,426 [1,407–1,444] Percentile 77 · #30 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,426 ±14 | 1,446 ±10 | 91.5% | 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: 한국어 1,419 [1,402–1,436] Percentile 69 · #43 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,403 ±12 | 1,438 ±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
B Language: Polski 1,430 [1,411–1,450] Percentile 76 · #32 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,453 ±13 | 1,452 ±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
B Language: Русский 1,417 [1,409–1,425] Percentile 70 · #70 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,427 ±4.93 | 1,432 ±4 | 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
History
The same in a table
| Model | 2026-10 |
|---|---|
| Inkling | 1,418 B |
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.