mpt-7b-chat in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
D 984 ±8
Percentile 2 · #287 · provisional
People prefer / Solves tasks
967 / —
Human votes vs benchmarks, Elo-eq
Value
—
On your hardware
Closed weights: cloud only.
Score decomposition
D General 984 [976–992] Percentile 2 · #287 · components: 4 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
955 ±5.98 | 955 ±6 | 35.8% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
896 ±11 | 939 ±10 | 28.7% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
907 ±9.25 | 946 ±9 | 15.4% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
901 ±15 | 946 ±13 | 5.8% | 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
D Coding 989 [966–1,012] Percentile 2 · #273 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
913 ±16 | 947 ±14 | 83.6% | 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 Math 979 [959–999] Percentile 2 · #251 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
919 ±13 | 932 ±12 | 82.7% | 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
D Writing 998 [976–1,020] Percentile 2 · #263 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
958 ±12 | 976 ±12 | 90.5% | 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 Language: English 963 [951–976] Percentile 2 · #267 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
981 ±6.56 | 945 ±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 |
|---|---|
| mpt-7b-chat | 984 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.