GLM 5V Turbo in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
B 1,407 ±3
Percentile 73 · #80 · provisional
People prefer / Solves tasks
1,420 / —
Human votes vs benchmarks, Elo-eq
Value
+14
$1.90 per 1M tokens, median of 15 providers · vendor $1.90
On your hardware
Closed weights: cloud only.
Score decomposition
B General 1,407 [1,404–1,410] Percentile 73 · #80 · components: 6 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,437 ±3.27 | 1,437 ±3 | 26.2% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,443 ±3.88 | 1,434 ±4 | 26.0% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,423 ±5.13 | 1,435 ±5 | 12.4% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,452 ±8.57 | 1,437 ±7 | 11.3% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,438 ±4.58 | 1,436 ±4 | 6.4% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,431 ±7.58 | 1,427 ±7 | 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
B Coding 1,408 [1,403–1,412] Percentile 72 · #80 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
webdev/overall
|
1,400 ±6.73 | 1,421 ±2 | 47.1% | 2026-10-01 | — |
| LMArena |
text/coding
|
1,467 ±5.70 | 1,441 ±5 | 42.9% | 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 Math 1,392 [1,372–1,412] Percentile 64 · #92 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,440 ±13 | 1,432 ±12 | 82.6% | 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 Vision 1,429 [1,426–1,432] Percentile 65 · #40 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,264 ±2.78 | 1,442 ±2 | 62.9% | 2026-10-02 | — |
| LMArena |
vision/ocr
|
1,270 ±2.66 | 1,443 ±3 | 15.7% | 2026-10-02 | — |
| LMArena |
vision/diagram
|
1,285 ±3.80 | 1,450 ±3 | 15.4% | 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 Writing 1,425 [1,416–1,434] Percentile 77 · #63 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,416 ±7.20 | 1,444 ±7 | 59.2% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,438 ±4.58 | 1,436 ±4 | 33.9% | 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 1,425 [1,410–1,440] Percentile 76 · #55 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,488 ±11 | 1,443 ±8 | 92.4% | 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
A Language: English 1,429 [1,420–1,438] Percentile 81 · #52 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,454 ±4.60 | 1,444 ±5 | 93.5% | 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
B Language: Español 1,416 [1,388–1,445] Percentile 63 · #56 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,452 ±18 | 1,446 ±17 | 87.7% | 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
C Language: Français 1,402 [1,378–1,426] Percentile 48 · #71 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,442 ±15 | 1,425 ±14 | 89.6% | 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: Русский 1,418 [1,404–1,433] Percentile 72 · #67 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,432 ±8.96 | 1,435 ±8 | 92.6% | 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
History
The same in a table
| Model | 2026-10 |
|---|---|
| GLM 5V Turbo | 1,407 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.