R1 0528 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
B 1,378 ±6
Percentile 56 · #128
People prefer / Solves tasks
1,396 / 1,356
Human votes vs benchmarks, Elo-eq
Value
+2
$0.9583 per 1M tokens, median of 10 providers
On your hardware
Closed weights: cloud only.
Score decomposition
B General 1,378 [1,372–1,385] Percentile 56 · #128 · components: 8
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
141 ±1.05 | 1,369 ±8 | 38.1% | 2025-05-28 | — |
| LMArena |
text/overall
|
1,428 ±2.89 | 1,428 ±3 | 16.0% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,415 ±3.93 | 1,409 ±4 | 15.7% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,382 ±4.88 | 1,396 ±5 | 7.6% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,394 ±10 | 1,390 ±8 | 6.4% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,404 ±5.60 | 1,403 ±5 | 3.7% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,391 ±5.42 | 1,392 ±5 | 3.7% | 2026-10-02 | — |
| Epoch AI |
gpqa_diamond
decay ×0.26 |
0.76 ±0.02 | 1,395 ±11 | 1.4% | 2025-05-29 | — |
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 1,384 [1,375–1,393] Percentile 60 · #112 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,427 ±5.83 | 1,406 ±5 | 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
B Math 1,365 [1,349–1,381] Percentile 51 · #125 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,401 ±10 | 1,394 ±10 | 84.9% | 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 Writing 1,405 [1,397–1,414] Percentile 67 · #90 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,406 ±6.38 | 1,435 ±6 | 60.8% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,391 ±5.42 | 1,392 ±5 | 32.4% | 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
B Language: 繁體中文 1,393 [1,380–1,406] Percentile 54 · #104 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,443 ±9.03 | 1,408 ±7 | 92.9% | 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: Deutsch 1,388 [1,369–1,408] Percentile 50 · #73 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,405 ±13 | 1,406 ±11 | 91.3% | 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 1,413 [1,406–1,420] Percentile 68 · #87 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,437 ±3.76 | 1,427 ±4 | 93.7% | 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
B Language: 日本語 1,404 [1,387–1,422] Percentile 57 · #56 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,394 ±13 | 1,422 ±10 | 91.9% | 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 1,384 [1,360–1,408] Percentile 41 · #81 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,359 ±18 | 1,404 ±13 | 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
B Language: Polski 1,416 [1,405–1,427] Percentile 58 · #56 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,428 ±7.22 | 1,431 ±6 | 93.2% | 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 1,412 [1,400–1,424] Percentile 67 · #77 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,423 ±7.50 | 1,428 ±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
History
The same in a table
| Model | 2026-10 |
|---|---|
| R1 0528 | 1,378 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.