step-1o-turbo-202506 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
C 1,318 ±4
Percentile 38 · #182 · provisional
People prefer / Solves tasks
1,326 / —
Human votes vs benchmarks, Elo-eq
Value
—
On your hardware
Closed weights: cloud only.
Score decomposition
C General 1,318 [1,314–1,322] Percentile 38 · #182 · components: 6 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,336 ±3.51 | 1,336 ±4 | 27.5% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,335 ±5.05 | 1,336 ±5 | 26.6% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,310 ±6.55 | 1,328 ±6 | 12.4% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,308 ±14 | 1,319 ±11 | 9.3% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,341 ±8.24 | 1,345 ±8 | 5.8% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,349 ±8.37 | 1,353 ±8 | 5.7% | 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 Coding 1,313 [1,302–1,325] Percentile 34 · #184 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,339 ±7.60 | 1,327 ±7 | 88.9% | 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 Math 1,296 [1,277–1,315] Percentile 35 · #166 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,318 ±12 | 1,315 ±12 | 83.3% | 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 Vision 1,355 [1,346–1,364] Percentile 31 · #78 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,186 ±7.24 | 1,372 ±6 | 66.4% | 2026-10-02 | — |
| LMArena |
vision/ocr
|
1,178 ±8.58 | 1,353 ±8 | 15.1% | 2026-10-02 | — |
| LMArena |
vision/diagram
|
1,185 ±15 | 1,361 ±13 | 11.1% | 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
C Writing 1,330 [1,318–1,343] Percentile 45 · #149 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,308 ±9.69 | 1,334 ±10 | 58.8% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,349 ±8.37 | 1,353 ±8 | 33.2% | 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
C Language: 繁體中文 1,344 [1,326–1,363] Percentile 37 · #141 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,379 ±13 | 1,358 ±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: Deutsch 1,316 [1,292–1,340] Percentile 27 · #106 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,315 ±16 | 1,329 ±14 | 89.6% | 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 1,330 [1,320–1,339] Percentile 39 · #166 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,353 ±4.95 | 1,338 ±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
D Language: Polski 1,318 [1,306–1,330] Percentile 8 · #121 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,304 ±7.90 | 1,326 ±7 | 93.0% | 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: Русский 1,330 [1,312–1,347] Percentile 34 · #154 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,327 ±11 | 1,341 ±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
History
The same in a table
| Model | 2026-10 |
|---|---|
| step-1o-turbo-202506 | 1,318 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.