grok-3-mini-high in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
C 1,356 ±7
Percentile 50 · #148
People prefer / Solves tasks
1,362 / 1,349
Human votes vs benchmarks, Elo-eq
Value
+4
$0.35 per 1M tokens, median of 1 providers
On your hardware
Closed weights: cloud only.
Score decomposition
C General 1,356 [1,349–1,363] Percentile 50 · #148 · components: 8
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
140 ±1.15 | 1,362 ±9 | 37.1% | 2025-06-24 | — |
| LMArena |
text/overall
|
1,369 ±2.78 | 1,369 ±3 | 16.3% | 2026-10-02 | high |
| LMArena |
text/hard_prompts
|
1,374 ±3.69 | 1,371 ±3 | 16.1% | 2026-10-02 | high |
| LMArena |
text/instruction_following
|
1,356 ±4.70 | 1,372 ±4 | 7.8% | 2026-10-02 | high |
| LMArena |
text/expert
|
1,395 ±9.69 | 1,390 ±8 | 6.6% | 2026-10-02 | high |
| LMArena |
text/longer_query
|
1,372 ±5.31 | 1,374 ±5 | 3.8% | 2026-10-02 | high |
| LMArena |
text/multi_turn
|
1,355 ±6.02 | 1,358 ±6 | 3.7% | 2026-10-02 | high |
| Epoch AI |
gpqa_diamond
decay ×0.26 |
0.76 ±0.03 | 1,394 ±14 | 1.2% | 2025-04-10 | low |
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 1,346 [1,338–1,355] Percentile 42 · #161 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,379 ±5.31 | 1,363 ±5 | 89.7% | 2026-10-02 | 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 Math 1,354 [1,339–1,369] Percentile 47 · #136 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,386 ±9.39 | 1,380 ±9 | 85.5% | 2026-10-02 | 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 Writing 1,360 [1,352–1,368] Percentile 51 · #131 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,342 ±5.92 | 1,369 ±6 | 61.2% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,372 ±5.31 | 1,374 ±5 | 32.1% | 2026-10-02 | 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 Language: 繁體中文 1,351 [1,336–1,366] Percentile 38 · #138 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,386 ±10 | 1,363 ±8 | 92.5% | 2026-10-02 | 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 Language: Deutsch 1,343 [1,321–1,366] Percentile 31 · #100 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,349 ±15 | 1,359 ±13 | 90.3% | 2026-10-02 | 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 Language: English 1,355 [1,348–1,363] Percentile 48 · #142 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,379 ±3.71 | 1,366 ±4 | 93.7% | 2026-10-02 | 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 Language: Español 1,361 [1,337–1,386] Percentile 26 · #110 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,379 ±15 | 1,380 ±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
C Language: 日本語 1,369 [1,352–1,387] Percentile 39 · #79 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,343 ±13 | 1,384 ±10 | 91.9% | 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
D Language: Polski 1,358 [1,346–1,370] Percentile 20 · #105 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,356 ±7.81 | 1,370 ±7 | 93.0% | 2026-10-02 | 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 Language: Русский 1,353 [1,341–1,365] Percentile 41 · #139 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,353 ±7.16 | 1,364 ±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
History
The same in a table
| Model | 2026-10 |
|---|---|
| grok-3-mini-high | 1,356 C |
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.