gemini-2.5-flash-preview-09-2025 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
B 1,382 ±9
Percentile 59 · #120
People prefer / Solves tasks
1,393 / 1,364
Human votes vs benchmarks, Elo-eq
Value
+8
$0.85 per 1M tokens, median of 2 providers
On your hardware
Closed weights: cloud only.
Score decomposition
B General 1,382 [1,373–1,391] Percentile 59 · #120 · components: 7
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
143 ±1.78 | 1,383 ±14 | 33.0% | 2025-09-25 | — |
| LMArena |
text/overall
|
1,407 ±2.06 | 1,406 ±2 | 17.4% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,409 ±2.62 | 1,403 ±2 | 17.3% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,394 ±3.35 | 1,407 ±3 | 8.5% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,418 ±7.13 | 1,409 ±6 | 7.7% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,406 ±3.53 | 1,406 ±3 | 4.2% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,397 ±4.11 | 1,396 ±4 | 4.2% | 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 Coding 1,364 [1,358–1,370] Percentile 50 · #140 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,400 ±3.79 | 1,382 ±3 | 90.1% | 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
B Math 1,382 [1,371–1,392] Percentile 58 · #109 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,415 ±6.61 | 1,408 ±6 | 87.2% | 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 Vision 1,415 [1,409–1,422] Percentile 55 · #51 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,254 ±4.96 | 1,433 ±4 | 64.7% | 2026-10-02 | — |
| LMArena |
vision/ocr
|
1,255 ±5.97 | 1,428 ±6 | 15.4% | 2026-10-02 | — |
| LMArena |
vision/diagram
|
1,249 ±9.48 | 1,418 ±8 | 13.4% | 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 Writing 1,399 [1,393–1,405] Percentile 64 · #97 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,387 ±4.63 | 1,415 ±5 | 61.4% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,406 ±3.53 | 1,406 ±3 | 32.2% | 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 1,399 [1,390–1,408] Percentile 57 · #97 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,449 ±6.21 | 1,413 ±5 | 93.5% | 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 1,400 [1,382–1,419] Percentile 57 · #63 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,419 ±12 | 1,418 ±10 | 91.6% | 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
B Language: English 1,390 [1,384–1,395] Percentile 59 · #113 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,413 ±2.85 | 1,402 ±3 | 93.9% | 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
C Language: Español 1,387 [1,370–1,404] Percentile 39 · #91 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,405 ±10 | 1,403 ±9 | 92.0% | 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
C Language: Français 1,397 [1,377–1,418] Percentile 46 · #74 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,433 ±13 | 1,417 ±12 | 90.9% | 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
B Language: 日本語 1,407 [1,386–1,429] Percentile 60 · #52 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,402 ±16 | 1,428 ±12 | 90.6% | 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
B Language: 한국어 1,406 [1,390–1,423] Percentile 59 · #56 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,385 ±12 | 1,424 ±9 | 92.2% | 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: Polski 1,400 [1,388–1,414] Percentile 45 · #73 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,410 ±8.39 | 1,416 ±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
B Language: Русский 1,388 [1,379–1,396] Percentile 54 · #107 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,393 ±5.37 | 1,400 ±5 | 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
History
The same in a table
| Model | 2026-10 |
|---|---|
| gemini-2.5-flash-preview-09-2025 | 1,382 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.