mpt-30b-chat in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
D 1,096 ±9
Percentile 9 · #266 · provisional
People prefer / Solves tasks
1,087 / —
Human votes vs benchmarks, Elo-eq
Value
—
On your hardware
Closed weights: cloud only.
Score decomposition
D General 1,096 [1,087–1,104] Percentile 9 · #266 · components: 4 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,069 ±6.17 | 1,069 ±6 | 37.7% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,052 ±14 | 1,080 ±12 | 26.5% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,054 ±11 | 1,085 ±10 | 15.0% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,054 ±16 | 1,085 ±15 | 5.6% | 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 Writing 1,107 [1,081–1,133] Percentile 10 · #240 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,074 ±15 | 1,095 ±15 | 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
D Language: English 1,083 [1,069–1,096] Percentile 10 · #247 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,102 ±6.97 | 1,073 ±7 | 92.8% | 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 |
|---|---|
| mpt-30b-chat | 1,096 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.