GLM 4.6V in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
C 1,347 ±6
Percentile 47 · #157 · provisional
People prefer / Solves tasks
1,357 / —
Human votes vs benchmarks, Elo-eq
Value
-12
$0.45 per 1M tokens, median of 11 providers · vendor $0.45
On your hardware
- GPU 12 GB #20 · Q4_0 · ≈6 tok/s
- GPU 24 GB #20 · Q3_K_S · ≈10 tok/s
- Mac 64 GB #22 · UD-IQ2_M · strong compression · ≈27 tok/s
- 128 GB unified memory #29 · Q5_K_M · ≈11 tok/s
Score decomposition
C General 1,347 [1,340–1,353] Percentile 47 · #157 · components: 5 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,377 ±5.68 | 1,377 ±6 | 31.9% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,368 ±7.59 | 1,366 ±7 | 30.2% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,351 ±11 | 1,366 ±10 | 12.5% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,358 ±11 | 1,361 ±10 | 6.1% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,360 ±13 | 1,362 ±12 | 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
C Coding 1,349 [1,330–1,367] Percentile 44 · #156 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,390 ±13 | 1,372 ±11 | 86.1% | 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 Vision 1,341 [1,332–1,350] Percentile 26 · #84 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,164 ±6.99 | 1,352 ±6 | 65.1% | 2026-10-02 | — |
| LMArena |
vision/ocr
|
1,171 ±8.30 | 1,347 ±8 | 14.9% | 2026-10-02 | — |
| LMArena |
vision/diagram
|
1,183 ±12 | 1,359 ±11 | 12.8% | 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
C Writing 1,353 [1,335–1,370] Percentile 49 · #137 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,347 ±14 | 1,375 ±15 | 54.3% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,358 ±11 | 1,361 ±10 | 35.7% | 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 Language: English 1,368 [1,352–1,385] Percentile 53 · #128 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,395 ±8.64 | 1,383 ±9 | 92.1% | 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: Русский 1,338 [1,314–1,362] Percentile 38 · #146 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,341 ±15 | 1,354 ±14 | 89.8% | 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 |
|---|---|
| GLM 4.6V | 1,347 C |
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.