GLM 4.7 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
B 1,398 ±6
Percentile 67 · #98
People prefer / Solves tasks
1,416 / 1,373
Human votes vs benchmarks, Elo-eq
Value
+20
$1 per 1M tokens, median of 22 providers · vendor $1
On your hardware
- 128 GB unified memory #39 · UD-IQ1_M · strong compression · ≈10 tok/s
Score decomposition
B General 1,398 [1,392–1,404] Percentile 67 · #98 · components: 9
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
144 ±1.09 | 1,386 ±9 | 33.4% | 2025-12-22 | — |
| LMArena |
text/overall
|
1,436 ±3.07 | 1,436 ±3 | 16.3% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,443 ±3.92 | 1,433 ±4 | 16.0% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,411 ±5.23 | 1,424 ±5 | 7.6% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,424 ±10 | 1,414 ±8 | 6.4% | 2026-10-02 | — |
| Epoch AI |
simpleqa_verified
decay ×0.61 |
0.32 ±0.01 | 1,398 ±5 | 4.1% | 2026-08-27 | — |
| LMArena |
text/longer_query
|
1,432 ±5.26 | 1,431 ±5 | 3.8% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,446 ±6.84 | 1,441 ±6 | 3.6% | 2026-10-02 | — |
| Epoch AI |
gpqa_diamond
decay ×0.26 |
0.83 ±0.02 | 1,427 ±11 | 1.3% | 2026-01-29 | — |
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
B Coding 1,408 [1,403–1,412] Percentile 71 · #81 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
webdev/overall
|
1,434 ±6.14 | 1,431 ±2 | 47.4% | 2026-10-01 | — |
| LMArena |
text/coding
|
1,454 ±5.98 | 1,430 ±5 | 42.6% | 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
B Math 1,383 [1,366–1,400] Percentile 60 · #103 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,423 ±10 | 1,416 ±10 | 84.7% | 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
B Writing 1,414 [1,406–1,423] Percentile 72 · #75 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,401 ±6.69 | 1,430 ±7 | 60.3% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,432 ±5.26 | 1,431 ±5 | 32.9% | 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
B Language: 繁體中文 1,432 [1,418–1,445] Percentile 79 · #48 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,495 ±9.23 | 1,449 ±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
A Language: English 1,429 [1,420–1,437] Percentile 81 · #53 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,453 ±4.41 | 1,444 ±5 | 93.6% | 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
B Language: Español 1,405 [1,379–1,430] Percentile 52 · #72 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,433 ±16 | 1,429 ±15 | 89.2% | 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
C Language: Français 1,391 [1,364–1,418] Percentile 40 · #82 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,432 ±17 | 1,416 ±16 | 88.4% | 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
B Language: Polski 1,416 [1,397–1,436] Percentile 58 · #55 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,435 ±13 | 1,437 ±11 | 91.2% | 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
B Language: Русский 1,412 [1,401–1,424] Percentile 68 · #76 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,423 ±7.03 | 1,428 ±6 | 93.2% | 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
History
The same in a table
| Model | 2026-10 |
|---|---|
| GLM 4.7 | 1,398 B |
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.