Grok 4.3 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
B 1,393 ±4
Percentile 64 · #106
People prefer / Solves tasks
1,380 / 1,411
Human votes vs benchmarks, Elo-eq
Value
+4
$1.56 per 1M tokens, median of 28 providers · vendor $1.56
On your hardware
Closed weights: cloud only.
Score decomposition
B General 1,393 [1,389–1,398] Percentile 64 · #106 · components: 9
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
149 ±0.80 | 1,431 ±6 | 34.8% | 2026-04-17 | — |
| LMArena |
text/overall
|
1,397 ±1.85 | 1,397 ±2 | 15.4% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,396 ±2.20 | 1,392 ±2 | 15.3% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,365 ±2.68 | 1,380 ±2 | 7.6% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,385 ±3.99 | 1,382 ±3 | 7.4% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,393 ±2.53 | 1,394 ±2 | 3.8% | 2026-10-02 | — |
| Epoch AI |
simpleqa_verified
decay ×0.61 |
0.33 ±0.01 | 1,402 ±5 | 3.8% | 2026-08-27 | high |
| LMArena |
text/multi_turn
|
1,405 ±3.32 | 1,404 ±3 | 3.8% | 2026-10-02 | — |
| Epoch AI |
gpqa_diamond
decay ×0.26 |
0.89 ±0.02 | 1,453 ±9 | 1.3% | 2026-06-17 | high |
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 1,382 [1,380–1,385] Percentile 58 · #116 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
webdev/overall
|
1,357 ±3.17 | 1,409 ±1 | 45.8% | 2026-10-01 | — |
| LMArena |
text/coding
|
1,414 ±2.86 | 1,394 ±3 | 44.6% | 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 1,382 [1,375–1,389] Percentile 58 · #108 · components: 3
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,388 ±5.48 | 1,381 ±5 | 51.9% | 2026-10-02 | — |
| Epoch AI |
frontiermath_t1_3
decay ×0.86 |
0.43 ±0.03 | 1,414 ±6 | 28.4% | 2026-06-17 | high |
| Epoch AI |
frontiermath_t4
decay ×0.86 |
0.15 ±0.06 | 1,416 ±9 | 12.4% | 2026-06-17 | high |
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 1,398 [1,394–1,401] Percentile 45 · #63 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,229 ±3.04 | 1,411 ±3 | 63.0% | 2026-10-02 | — |
| LMArena |
vision/ocr
|
1,235 ±3.05 | 1,408 ±3 | 15.7% | 2026-10-02 | — |
| LMArena |
vision/diagram
|
1,239 ±4.35 | 1,409 ±4 | 15.3% | 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 Search 1,393 [1,388–1,398] Percentile 34 · #22 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
search/overall
|
1,165 ±2.63 | 1,405 ±3 | 93.9% | 2026-08-24 | — |
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 1,391 [1,387–1,395] Percentile 61 · #105 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,380 ±3.32 | 1,408 ±3 | 62.1% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,393 ±2.53 | 1,394 ±2 | 31.8% | 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 Language: 繁體中文 1,379 [1,372–1,386] Percentile 47 · #118 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,422 ±4.89 | 1,391 ±4 | 93.8% | 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 Language: Deutsch 1,382 [1,367–1,398] Percentile 48 · #76 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,394 ±9.85 | 1,397 ±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
B Language: English 1,381 [1,376–1,386] Percentile 57 · #119 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,404 ±2.40 | 1,392 ±2 | 94.0% | 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
C Language: Español 1,383 [1,371–1,396] Percentile 36 · #96 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,398 ±7.47 | 1,397 ±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
C Language: Français 1,385 [1,373–1,396] Percentile 37 · #85 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,412 ±7.05 | 1,398 ±6 | 93.1% | 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: 日本語 1,396 [1,380–1,411] Percentile 50 · #65 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,380 ±11 | 1,412 ±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
C Language: 한국어 1,387 [1,374–1,401] Percentile 44 · #76 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,356 ±9.83 | 1,402 ±8 | 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
C Language: Polski 1,391 [1,377–1,405] Percentile 39 · #80 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,398 ±8.95 | 1,406 ±8 | 92.7% | 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: Русский 1,393 [1,386–1,399] Percentile 57 · #102 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,398 ±3.90 | 1,406 ±4 | 93.8% | 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 |
|---|---|
| Grok 4.3 | 1,393 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.