step-3 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
C 1,332 ±4
Percentile 43 · #168 · provisional
People prefer / Solves tasks
1,340 / —
Human votes vs benchmarks, Elo-eq
Value
-17
$0.30 per 1M tokens, median of 1 providers
On your hardware
Closed weights: cloud only.
Score decomposition
C General 1,332 [1,327–1,336] Percentile 43 · #168 · components: 5 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,351 ±3.81 | 1,351 ±4 | 31.2% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,355 ±5.44 | 1,354 ±5 | 30.0% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,332 ±7.35 | 1,349 ±7 | 13.6% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,326 ±8.31 | 1,332 ±8 | 6.5% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,341 ±9.31 | 1,345 ±8 | 6.3% | 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
C Coding 1,335 [1,322–1,348] Percentile 38 · #173 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,367 ±8.47 | 1,352 ±8 | 88.4% | 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 1,329 [1,305–1,353] Percentile 39 · #157 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,366 ±16 | 1,361 ±15 | 79.7% | 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
C Vision 1,346 [1,338–1,354] Percentile 27 · #83 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,177 ±5.98 | 1,363 ±5 | 67.8% | 2026-10-02 | — |
| LMArena |
vision/ocr
|
1,169 ±8.68 | 1,345 ±8 | 14.6% | 2026-10-02 | — |
| LMArena |
vision/diagram
|
1,155 ±16 | 1,334 ±14 | 10.4% | 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 Writing 1,331 [1,317–1,344] Percentile 45 · #147 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,322 ±11 | 1,348 ±11 | 57.3% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,326 ±8.31 | 1,332 ±8 | 34.5% | 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 1,354 [1,331–1,378] Percentile 40 · #134 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,396 ±17 | 1,371 ±13 | 90.0% | 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: English 1,349 [1,338–1,360] Percentile 45 · #151 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,373 ±5.60 | 1,360 ±6 | 93.3% | 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 Language: Polski 1,312 [1,291–1,333] Percentile 5 · #124 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,301 ±14 | 1,323 ±12 | 90.7% | 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
C Language: Русский 1,332 [1,311–1,353] Percentile 35 · #152 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,331 ±13 | 1,345 ±12 | 90.8% | 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
History
The same in a table
| Model | 2026-10 |
|---|---|
| step-3 | 1,332 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.