Grok 4.1 Fast (Search) in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
B 1,377 ±2
Percentile 53 · #139 · provisional
People prefer / Solves tasks
1,388 / —
Human votes vs benchmarks, Elo-eq
Value
+43
$0.275 per 1M tokens, median of 6 providers
On your hardware
Closed weights: cloud only.
Score decomposition
B General 1,377 [1,375–1,379] Percentile 53 · #139 · components: 6 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,408 ±1.63 | 1,408 ±2 | 25.7% | 2026-11-11 | reasoning |
| LMArena |
text/hard_prompts
|
1,408 ±2.07 | 1,402 ±2 | 25.6% | 2026-11-11 | reasoning |
| LMArena |
text/instruction_following
|
1,376 ±2.63 | 1,391 ±2 | 12.6% | 2026-11-11 | reasoning |
| LMArena |
text/expert
|
1,399 ±4.69 | 1,394 ±4 | 12.2% | 2026-11-11 | reasoning |
| LMArena |
text/longer_query
|
1,390 ±2.61 | 1,391 ±2 | 6.3% | 2026-11-11 | reasoning |
| LMArena |
text/multi_turn
|
1,389 ±3.27 | 1,389 ±3 | 6.2% | 2026-11-11 | 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
C Coding 1,363 [1,361–1,366] Percentile 47 · #153 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
webdev/overall
|
1,242 ±5.70 | 1,376 ±2 | 44.7% | 2026-11-15 | reasoning |
| LMArena |
text/coding
|
1,412 ±2.86 | 1,392 ±3 | 44.0% | 2026-11-11 | 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 Math 1,376 [1,368–1,385] Percentile 52 · #123 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,407 ±5.12 | 1,400 ±5 | 87.8% | 2026-11-11 | 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
C Vision 1,372 [1,367–1,376] Percentile 33 · #75 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,201 ±3.50 | 1,386 ±3 | 63.3% | 2026-11-09 | reasoning |
| LMArena |
vision/ocr
|
1,195 ±3.78 | 1,370 ±4 | 15.6% | 2026-11-09 | reasoning |
| LMArena |
vision/diagram
|
1,211 ±5.59 | 1,384 ±5 | 14.9% | 2026-11-09 | 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
C Search 1,400 [1,395–1,405] Percentile 26 · #27 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
search/overall
|
1,172 ±2.56 | 1,412 ±3 | 94.0% | 2026-11-09 | search |
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 1,400 [1,395–1,404] Percentile 63 · #98 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,395 ±3.43 | 1,424 ±4 | 62.0% | 2026-11-11 | reasoning |
| LMArena |
text/longer_query
|
1,390 ±2.61 | 1,391 ±2 | 31.8% | 2026-11-11 | 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 Language: 繁體中文 1,393 [1,386–1,400] Percentile 51 · #107 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,440 ±4.67 | 1,406 ±4 | 93.8% | 2026-11-11 | 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
C Language: Deutsch 1,389 [1,374–1,405] Percentile 49 · #75 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,403 ±10 | 1,405 ±9 | 92.3% | 2026-11-11 | 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 Language: English 1,397 [1,392–1,401] Percentile 60 · #108 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,420 ±2.30 | 1,409 ±2 | 94.0% | 2026-11-11 | 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
C Language: Español 1,396 [1,382–1,409] Percentile 38 · #93 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,413 ±7.77 | 1,410 ±7 | 92.9% | 2026-11-11 | 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
C Language: Français 1,386 [1,372–1,400] Percentile 36 · #91 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,415 ±8.45 | 1,400 ±8 | 92.7% | 2026-11-11 | 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
C Language: 日本語 1,374 [1,355–1,394] Percentile 36 · #81 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,352 ±15 | 1,391 ±11 | 91.3% | 2026-11-11 | 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
C Language: 한국어 1,390 [1,376–1,405] Percentile 46 · #74 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,361 ±10 | 1,405 ±8 | 92.6% | 2026-11-11 | 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
C Language: Polski 1,393 [1,381–1,405] Percentile 37 · #83 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,400 ±7.87 | 1,407 ±7 | 93.0% | 2026-11-11 | 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 Language: Русский 1,384 [1,378–1,390] Percentile 50 · #115 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,388 ±3.69 | 1,396 ±3 | 93.8% | 2026-11-11 | 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
History
The same in a table
| Model | 2026-11 |
|---|---|
| Grok 4.1 Fast (Search) | 1,377 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.