chatglm-6b in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
D 969 ±8
Percentile 1 · #289 · provisional
People prefer / Solves tasks
951 / —
Human votes vs benchmarks, Elo-eq
Value
—
On your hardware
Closed weights: cloud only.
Score decomposition
D General 969 [962–977] Percentile 1 · #289 · components: 4 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
918 ±6.24 | 918 ±6 | 35.2% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
901 ±11 | 944 ±10 | 29.2% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
902 ±8.90 | 941 ±8 | 15.7% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
856 ±15 | 906 ±14 | 5.7% | 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 Coding 989 [969–1,009] Percentile 1 · #274 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
919 ±13 | 953 ±12 | 85.5% | 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 Math 984 [964–1,004] Percentile 2 · #249 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
926 ±13 | 938 ±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 945 [923–967] Percentile 0 · #267 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
900 ±12 | 918 ±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 922 [909–935] Percentile 1 · #271 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
938 ±6.84 | 900 ±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 |
|---|---|
| chatglm-6b | 969 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.