Grok 4.7 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
B 1,416 ±6
Percentile 77 · #67
People prefer / Solves tasks
1,393 / 1,444
Human votes vs benchmarks, Elo-eq
Value
+11
$3 per 1M tokens, median of 17 providers · vendor $3
On your hardware
Closed weights: cloud only.
Score decomposition
B General 1,416 [1,410–1,422] Percentile 77 · #67 · components: 9
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
154 ±1.02 | 1,466 ±8 | 34.8% | 2026-09-21 | — |
| LMArena |
text/overall
|
1,400 ±3.96 | 1,400 ±4 | 16.0% | 2026-10-02 | xhigh |
| LMArena |
text/hard_prompts
|
1,413 ±4.98 | 1,406 ±4 | 15.7% | 2026-10-02 | xhigh |
| LMArena |
text/instruction_following
|
1,409 ±6.58 | 1,422 ±6 | 7.3% | 2026-10-02 | xhigh |
| LMArena |
text/expert
|
1,414 ±12 | 1,406 ±10 | 6.1% | 2026-10-02 | xhigh |
| Epoch AI |
simpleqa_verified
decay ×0.61 |
0.56 ±0.02 | 1,473 ±5 | 4.1% | 2026-09-22 | xhigh |
| LMArena |
text/longer_query
|
1,417 ±6.07 | 1,416 ±6 | 3.7% | 2026-10-02 | xhigh |
| LMArena |
text/multi_turn
|
1,396 ±9.81 | 1,396 ±9 | 3.2% | 2026-10-02 | xhigh |
| Epoch AI |
gpqa_diamond
decay ×0.26 |
0.93 ±0.02 | 1,471 ±7 | 1.6% | 2026-09-22 | xhigh |
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 Coding 1,430 [1,425–1,434] Percentile 83 · #49 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
webdev/overall
|
1,638 ±6.00 | 1,489 ±2 | 61.7% | 2026-10-01 | xhigh |
| LMArena |
text/coding
outlier |
1,423 ±8.21 | 1,402 ±7 | 25.2% | 2026-10-02 | xhigh |
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 Agents 1,448 [1,441–1,454] Percentile 67 · #20 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
agent/overall
|
0.04 ±0.01 | 1,475 ±4 | 90.0% | 2026-10-02 | xhigh |
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 1,400 [1,387–1,413] Percentile 72 · #73 · components: 3
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
frontiermath_t1_3
decay ×0.86 |
0.53 ±0.03 | 1,436 ±6 | 37.9% | 2026-09-22 | xhigh |
| LMArena |
text/math
|
1,415 ±17 | 1,407 ±16 | 36.4% | 2026-10-02 | xhigh |
| Epoch AI |
frontiermath_t4
decay ×0.86 |
0.17 ±0.06 | 1,420 ±10 | 16.0% | 2026-09-22 | xhigh |
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 1,408 [1,397–1,418] Percentile 68 · #85 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,400 ±8.24 | 1,428 ±8 | 58.9% | 2026-10-02 | xhigh |
| LMArena |
text/longer_query
|
1,417 ±6.07 | 1,416 ±6 | 33.9% | 2026-10-02 | xhigh |
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 1,402 [1,384–1,421] Percentile 58 · #94 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,459 ±13 | 1,421 ±10 | 91.6% | 2026-10-02 | xhigh |
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 1,379 [1,368–1,391] Percentile 56 · #120 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,404 ±6.11 | 1,392 ±6 | 93.1% | 2026-10-02 | xhigh |
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 [1,377–1,410] Percentile 58 · #100 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,403 ±10 | 1,410 ±9 | 92.2% | 2026-10-02 | xhigh |
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 4.7 | 1,416 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.