Gemini 3.5 Flash Lite in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
B 1,403 ±6
Percentile 70 · #89
People prefer / Solves tasks
1,418 / 1,384
Human votes vs benchmarks, Elo-eq
Value
+29
$0.85 per 1M tokens, median of 23 providers · vendor $0.85
On your hardware
Closed weights: cloud only.
Score decomposition
B General 1,403 [1,398–1,409] Percentile 70 · #89 · components: 8
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
145 ±0.94 | 1,399 ±7 | 38.2% | 2026-07-21 | — |
| LMArena |
text/overall
|
1,435 ±2.28 | 1,435 ±2 | 15.5% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,440 ±2.68 | 1,431 ±2 | 15.5% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,419 ±3.24 | 1,432 ±3 | 7.6% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,433 ±4.99 | 1,422 ±4 | 7.4% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,435 ±3.06 | 1,433 ±3 | 3.8% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,444 ±4.33 | 1,439 ±4 | 3.7% | 2026-10-02 | — |
| Epoch AI |
gpqa_diamond
decay ×0.26 |
0.83 ±0.03 | 1,427 ±12 | 1.2% | 2026-08-06 | 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 Coding 1,406 [1,400–1,412] Percentile 71 · #82 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,452 ±3.52 | 1,428 ±3 | 90.2% | 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 Math 1,390 [1,382–1,397] Percentile 63 · #96 · components: 3
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,434 ±7.52 | 1,426 ±7 | 47.0% | 2026-10-02 | — |
| Epoch AI |
frontiermath_t1_3
decay ×0.86 |
0.26 ±0.03 | 1,377 ±6 | 29.2% | 2026-08-02 | high |
| Epoch AI |
frontiermath_t4
decay ×0.86 |
0.00 ±0.00 | 1,393 ±0 | 16.6% | 2026-08-02 | 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 Vision 1,432 [1,426–1,437] Percentile 67 · #38 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,266 ±4.26 | 1,444 ±4 | 63.7% | 2026-10-02 | — |
| LMArena |
vision/ocr
|
1,279 ±4.64 | 1,452 ±4 | 15.6% | 2026-10-02 | — |
| LMArena |
vision/diagram
|
1,289 ±7.35 | 1,454 ±6 | 14.3% | 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 1,429 [1,424–1,434] Percentile 79 · #58 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,421 ±4.08 | 1,450 ±4 | 61.7% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,435 ±3.06 | 1,433 ±3 | 32.1% | 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 Language: 繁體中文 1,413 [1,404–1,422] Percentile 68 · #71 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,468 ±6.09 | 1,428 ±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 1,429 [1,410–1,448] Percentile 79 · #31 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,455 ±12 | 1,450 ±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 1,414 [1,408–1,420] Percentile 69 · #86 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,437 ±3.06 | 1,428 ±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: Español 1,416 [1,399–1,433] Percentile 62 · #58 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,439 ±10 | 1,434 ±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
B Language: Français 1,416 [1,399–1,432] Percentile 58 · #58 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,451 ±9.86 | 1,434 ±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
B Language: 日本語 1,426 [1,408–1,445] Percentile 79 · #28 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,427 ±14 | 1,447 ±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: 한국어 1,421 [1,405–1,438] Percentile 70 · #42 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,406 ±12 | 1,440 ±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
B Language: Polski 1,412 [1,392–1,432] Percentile 55 · #60 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,430 ±13 | 1,432 ±11 | 91.1% | 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 Language: Русский 1,431 [1,423–1,439] Percentile 79 · #49 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,444 ±4.96 | 1,446 ±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
History
The same in a table
| Model | 2026-10 |
|---|---|
| Gemini 3.5 Flash Lite | 1,403 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.