fastchat-t5-3b in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
D 931 ±8
Percentile 0 · #292 · provisional
People prefer / Solves tasks
910 / —
Human votes vs benchmarks, Elo-eq
Value
—
On your hardware
Closed weights: cloud only.
Score decomposition
D General 931 [924–939] Percentile 0 · #292 · components: 4 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
894 ±6.23 | 894 ±6 | 35.3% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
814 ±11 | 866 ±10 | 29.5% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
858 ±9.31 | 900 ±9 | 15.4% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
853 ±16 | 902 ±14 | 5.5% | 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 Coding 876 [853–898] Percentile 0 · #278 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
764 ±15 | 814 ±13 | 84.2% | 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 Math 934 [914–954] Percentile 0 · #255 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
862 ±13 | 877 ±13 | 82.4% | 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 Writing 946 [925–968] Percentile 1 · #266 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
902 ±12 | 920 ±12 | 90.6% | 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
D Language: English 918 [905–931] Percentile 0 · #272 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
935 ±6.78 | 896 ±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
History
The same in a table
| Model | 2026-10 |
|---|---|
| fastchat-t5-3b | 931 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.