grok-4.1-thinking in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
B 1,400 ±2
Percentile 68 · #95 · provisional
People prefer / Solves tasks
1,411 / —
Human votes vs benchmarks, Elo-eq
Value
-12
$4 per 1M tokens, median of 1 providers
On your hardware
Closed weights: cloud only.
Score decomposition
B General 1,400 [1,398–1,401] Percentile 68 · #95 · components: 6 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,437 ±1.61 | 1,437 ±2 | 25.6% | 2026-10-02 | thinking |
| LMArena |
text/hard_prompts
|
1,435 ±2.02 | 1,427 ±2 | 25.6% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,400 ±2.57 | 1,413 ±2 | 12.6% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,417 ±4.45 | 1,409 ±4 | 12.2% | 2026-10-02 | thinking |
| LMArena |
text/longer_query
|
1,416 ±2.54 | 1,415 ±2 | 6.3% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,438 ±3.15 | 1,433 ±3 | 6.3% | 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
B Coding 1,380 [1,377–1,382] Percentile 57 · #120 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
webdev/overall
|
1,241 ±5.65 | 1,376 ±2 | 45.6% | 2026-10-01 | fast-reasoning |
| LMArena |
text/coding
|
1,445 ±2.80 | 1,422 ±2 | 44.8% | 2026-10-02 | thinking |
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 1,389 [1,381–1,397] Percentile 62 · #98 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,422 ±4.91 | 1,414 ±5 | 87.9% | 2026-10-02 | thinking |
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 1,371 [1,367–1,376] Percentile 38 · #70 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,201 ±3.54 | 1,385 ±3 | 63.3% | 2026-10-02 | fast-reasoning |
| LMArena |
vision/ocr
|
1,195 ±3.78 | 1,370 ±4 | 15.6% | 2026-10-02 | fast-reasoning |
| LMArena |
vision/diagram
|
1,210 ±5.59 | 1,384 ±5 | 14.9% | 2026-10-02 | fast-reasoning |
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 1,418 [1,413–1,422] Percentile 73 · #72 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,411 ±3.37 | 1,440 ±3 | 62.0% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,416 ±2.54 | 1,415 ±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
B Language: 繁體中文 1,411 [1,405–1,418] Percentile 67 · #74 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,464 ±4.42 | 1,425 ±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
B Language: Deutsch 1,425 [1,411–1,439] Percentile 74 · #38 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,446 ±9.00 | 1,442 ±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: English 1,423 [1,419–1,427] Percentile 75 · #69 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,447 ±2.24 | 1,437 ±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
B Language: Español 1,418 [1,406–1,430] Percentile 64 · #55 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,438 ±7.27 | 1,434 ±7 | 93.0% | 2026-10-02 | thinking |
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: Français 1,414 [1,401–1,427] Percentile 55 · #61 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,448 ±7.97 | 1,430 ±7 | 92.8% | 2026-10-02 | thinking |
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: 日本語 1,407 [1,391–1,422] Percentile 58 · #54 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,396 ±11 | 1,424 ±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: 한국어 1,423 [1,410–1,436] Percentile 72 · #39 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,407 ±9.39 | 1,440 ±7 | 92.9% | 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
A Language: Polski 1,437 [1,426–1,448] Percentile 82 · #25 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,455 ±7.00 | 1,454 ±6 | 93.3% | 2026-10-02 | thinking |
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 1,423 [1,417–1,429] Percentile 75 · #60 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,434 ±3.63 | 1,437 ±3 | 93.9% | 2026-10-02 | thinking |
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-4.1-thinking | 1,400 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.