phi-3-mini-4k-instruct-june-2024 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
D 1,107 ±4
Percentile 12 · #257 · provisional
People prefer / Solves tasks
1,101 / —
Human votes vs benchmarks, Elo-eq
Value
—
On your hardware
Closed weights: cloud only.
Score decomposition
D General 1,107 [1,103–1,111] Percentile 12 · #257 · components: 6 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,080 ±3.24 | 1,080 ±3 | 27.5% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,087 ±5.48 | 1,113 ±5 | 26.0% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,058 ±4.89 | 1,089 ±5 | 13.1% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,051 ±13 | 1,109 ±11 | 9.5% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,049 ±7.48 | 1,080 ±7 | 6.0% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,042 ±9.51 | 1,066 ±9 | 5.3% | 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
D Coding 1,118 [1,107–1,129] Percentile 12 · #245 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,093 ±7.01 | 1,108 ±6 | 89.1% | 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
D Math 1,161 [1,150–1,173] Percentile 18 · #210 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,152 ±6.94 | 1,155 ±7 | 87.0% | 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
D Writing 1,076 [1,065–1,086] Percentile 7 · #249 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,045 ±7.39 | 1,065 ±8 | 63.2% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,042 ±9.51 | 1,066 ±9 | 29.3% | 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
D Language: 繁體中文 1,091 [1,078–1,104] Percentile 5 · #212 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,033 ±9.09 | 1,083 ±7 | 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
D Language: Deutsch 1,096 [1,072–1,121] Percentile 2 · #141 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,031 ±16 | 1,084 ±14 | 89.4% | 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
D Language: English 1,108 [1,100–1,116] Percentile 14 · #236 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,129 ±4.19 | 1,102 ±4 | 93.6% | 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
D Language: 日本語 1,104 [1,082–1,126] Percentile 2 · #126 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
954 ±17 | 1,094 ±12 | 90.4% | 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
D Language: Русский 1,075 [1,061–1,088] Percentile 3 · #228 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,019 ±8.52 | 1,064 ±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
History
The same in a table
| Model | 2026-10 |
|---|---|
| phi-3-mini-4k-instruct-june-2024 | 1,107 D |
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.