koala-13b in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
D 1,010 ±6
Percentile 3 · #285 · provisional
People prefer / Solves tasks
996 / —
Human votes vs benchmarks, Elo-eq
Value
—
On your hardware
Closed weights: cloud only.
Score decomposition
D General 1,010 [1,003–1,016] Percentile 3 · #285 · components: 4 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
990 ±4.95 | 990 ±5 | 34.9% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
930 ±9.03 | 971 ±8 | 29.9% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
944 ±7.63 | 981 ±7 | 15.7% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
923 ±12 | 966 ±11 | 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
D Coding 1,006 [988–1,024] Percentile 2 · #271 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
945 ±12 | 976 ±11 | 86.4% | 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 Math 984 [968–1,002] Percentile 3 · #248 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
932 ±11 | 944 ±10 | 84.5% | 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
D Writing 1,010 [991–1,029] Percentile 3 · #260 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
973 ±10 | 992 ±11 | 91.4% | 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: 繁體中文 985 [962–1,007] Percentile 0 · #222 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
881 ±16 | 962 ±12 | 90.4% | 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: English 1,003 [992–1,014] Percentile 4 · #263 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,022 ±5.62 | 988 ±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
History
The same in a table
| Model | 2026-10 |
|---|---|
| koala-13b | 1,010 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.