RWKV-4-Raven-14B in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
D 977 ±7
Percentile 2 · #288 · provisional
People prefer / Solves tasks
960 / —
Human votes vs benchmarks, Elo-eq
Value
—
On your hardware
Closed weights: cloud only.
Score decomposition
D General 977 [969–984] Percentile 2 · #288 · components: 4 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
948 ±5.74 | 948 ±6 | 35.2% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
896 ±10 | 940 ±9 | 29.3% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
883 ±8.41 | 923 ±8 | 15.7% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
894 ±14 | 939 ±12 | 6.0% | 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
D Coding 996 [976–1,016] Percentile 2 · #272 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
928 ±14 | 960 ±12 | 85.3% | 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 Math 980 [960–999] Percentile 2 · #250 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
922 ±12 | 934 ±12 | 83.2% | 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 Writing 975 [954–995] Percentile 2 · #264 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
934 ±11 | 952 ±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
D Language: English 951 [938–963] Percentile 2 · #268 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
968 ±6.38 | 932 ±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 |
|---|---|
| RWKV-4-Raven-14B | 977 D |
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.