Inkling Small in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
B 1,407 ±6
Percentile 72 · #82
People prefer / Solves tasks
1,403 / 1,413
Human votes vs benchmarks, Elo-eq
Value
+38
$0.675 per 1M tokens, median of 9 providers
On your hardware
- GPU 24 GB #24 · UD-IQ1_S · strong compression · ≈18 tok/s
- 128 GB unified memory #2 · UD-IQ3_S · ≈23 tok/s
Score decomposition
B General 1,407 [1,401–1,413] Percentile 72 · #82 · components: 9
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
150 ±1.17 | 1,439 ±9 | 32.3% | 2026-07-15 | — |
| LMArena |
text/overall
|
1,414 ±2.48 | 1,414 ±2 | 16.5% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,424 ±2.89 | 1,417 ±3 | 16.4% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,398 ±3.51 | 1,411 ±3 | 8.1% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,443 ±5.56 | 1,430 ±4 | 7.8% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,401 ±3.31 | 1,401 ±3 | 4.1% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,419 ±4.94 | 1,417 ±4 | 3.9% | 2026-10-02 | — |
| Epoch AI |
simpleqa_verified
outlier decay ×0.61 |
0.19 ±0.01 | 1,357 ±4 | 2.1% | 2026-08-27 | xhigh |
| Epoch AI |
gpqa_diamond
decay ×0.26 |
0.89 ±0.02 | 1,451 ±9 | 1.5% | 2026-08-14 | 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 1,404 [1,401–1,408] Percentile 70 · #85 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
webdev/overall
|
1,408 ±4.61 | 1,424 ±1 | 46.1% | 2026-10-01 | — |
| LMArena |
text/coding
|
1,453 ±3.83 | 1,428 ±3 | 44.2% | 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
D Agents 1,386 [1,380–1,392] Percentile 5 · #55 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
agent/overall
|
-0.10 ±0.01 | 1,406 ±3 | 90.1% | 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 Math 1,415 [1,406–1,424] Percentile 80 · #52 · components: 3
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,454 ±8.86 | 1,445 ±8 | 48.1% | 2026-10-02 | — |
| Epoch AI |
frontiermath_t1_3
decay ×0.86 |
0.46 ±0.03 | 1,421 ±6 | 30.9% | 2026-08-14 | xhigh |
| Epoch AI |
frontiermath_t4
decay ×0.86 |
0.17 ±0.06 | 1,420 ±10 | 13.1% | 2026-08-14 | 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
C Vision 1,402 [1,397–1,408] Percentile 47 · #60 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,234 ±4.37 | 1,416 ±4 | 63.8% | 2026-10-02 | — |
| LMArena |
vision/ocr
|
1,241 ±4.72 | 1,414 ±5 | 15.6% | 2026-10-02 | — |
| LMArena |
vision/diagram
|
1,252 ±7.51 | 1,421 ±7 | 14.2% | 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 Writing 1,361 [1,355–1,366] Percentile 52 · #130 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,329 ±4.55 | 1,356 ±5 | 61.4% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,401 ±3.31 | 1,401 ±3 | 32.3% | 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
B Language: 繁體中文 1,409 [1,399–1,418] Percentile 64 · #81 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,462 ±6.68 | 1,423 ±5 | 93.4% | 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 Language: Deutsch 1,387 [1,364–1,409] Percentile 49 · #74 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,405 ±15 | 1,406 ±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
B Language: English 1,397 [1,391–1,403] Percentile 62 · #104 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,421 ±3.31 | 1,410 ±4 | 93.8% | 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: Español 1,410 [1,392–1,429] Percentile 54 · #69 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,433 ±11 | 1,430 ±10 | 91.6% | 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: Français 1,396 [1,378–1,415] Percentile 43 · #77 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,430 ±11 | 1,414 ±10 | 91.6% | 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: 日本語 1,410 [1,389–1,431] Percentile 62 · #49 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,405 ±16 | 1,431 ±12 | 90.9% | 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: 한국어 1,385 [1,367–1,404] Percentile 43 · #78 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,356 ±14 | 1,402 ±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
C Language: Polski 1,407 [1,384–1,430] Percentile 49 · #67 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,426 ±16 | 1,430 ±13 | 90.1% | 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: Русский 1,386 [1,377–1,395] Percentile 52 · #112 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,391 ±5.59 | 1,399 ±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
History
The same in a table
| Model | 2026-10 |
|---|---|
| Inkling Small | 1,407 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.