Gemini 2.5 Flash in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
B 1,380 ±6
Percentile 58 · #123
People prefer / Solves tasks
1,403 / 1,353
Human votes vs benchmarks, Elo-eq
Value
+7
$0.85 per 1M tokens, median of 29 providers · vendor $0.85
On your hardware
Closed weights: cloud only.
Score decomposition
B General 1,380 [1,374–1,387] Percentile 58 · #123 · components: 7
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
141 ±0.95 | 1,365 ±8 | 41.8% | 2025-06-17 | — |
| LMArena |
text/overall
|
1,417 ±1.23 | 1,417 ±1 | 14.9% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,422 ±1.58 | 1,415 ±1 | 14.8% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,405 ±1.92 | 1,418 ±2 | 7.4% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,425 ±3.41 | 1,415 ±3 | 7.2% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,419 ±2.00 | 1,418 ±2 | 3.7% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,408 ±2.33 | 1,406 ±2 | 3.7% | 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 Coding 1,383 [1,380–1,387] Percentile 59 · #115 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,424 ±2.14 | 1,402 ±2 | 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
B Math 1,380 [1,374–1,386] Percentile 57 · #111 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,410 ±3.40 | 1,403 ±3 | 88.4% | 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
C Vision 1,402 [1,400–1,405] Percentile 48 · #59 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,235 ±2.32 | 1,416 ±2 | 63.0% | 2026-10-02 | — |
| LMArena |
vision/ocr
|
1,237 ±2.49 | 1,411 ±2 | 15.7% | 2026-10-02 | — |
| LMArena |
vision/diagram
|
1,245 ±3.66 | 1,415 ±3 | 15.3% | 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 Writing 1,412 [1,408–1,415] Percentile 70 · #81 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,400 ±2.53 | 1,429 ±3 | 62.4% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,419 ±2.00 | 1,418 ±2 | 31.6% | 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: 繁體中文 1,400 [1,396–1,405] Percentile 58 · #95 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,450 ±3.37 | 1,413 ±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
B Language: Deutsch 1,403 [1,394–1,413] Percentile 60 · #58 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,417 ±6.11 | 1,417 ±5 | 93.4% | 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: English 1,395 [1,391–1,398] Percentile 61 · #106 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,418 ±1.66 | 1,407 ±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 1,404 [1,394–1,414] Percentile 51 · #74 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,421 ±5.61 | 1,418 ±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
C Language: Français 1,401 [1,390–1,412] Percentile 47 · #72 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,431 ±6.47 | 1,416 ±6 | 93.3% | 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 Language: 日本語 1,409 [1,400–1,419] Percentile 61 · #50 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,396 ±7.18 | 1,424 ±5 | 93.4% | 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 1,410 [1,400–1,419] Percentile 62 · #52 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,386 ±6.78 | 1,424 ±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
C Language: Polski 1,405 [1,399–1,412] Percentile 48 · #68 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,413 ±4.22 | 1,419 ±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: Русский 1,407 [1,403–1,412] Percentile 65 · #83 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,415 ±2.82 | 1,420 ±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
History
The same in a table
| Model | 2026-10 |
|---|---|
| Gemini 2.5 Flash | 1,380 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.