gemini-2.5-flash-lite-preview-09-2025-no-thinking in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
C 1,355 ±2
Percentile 48 · #152 · provisional
People prefer / Solves tasks
1,364 / —
Human votes vs benchmarks, Elo-eq
Value
+19
$0.175 per 1M tokens, median of 3 providers
On your hardware
Closed weights: cloud only.
Score decomposition
C General 1,355 [1,353–1,357] Percentile 48 · #152 · components: 6 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,379 ±1.74 | 1,379 ±2 | 25.8% | 2026-10-02 | no-thinking |
| LMArena |
text/hard_prompts
|
1,377 ±2.24 | 1,374 ±2 | 25.7% | 2026-10-02 | no-thinking |
| LMArena |
text/instruction_following
|
1,355 ±2.87 | 1,370 ±3 | 12.6% | 2026-10-02 | no-thinking |
| LMArena |
text/expert
|
1,373 ±5.59 | 1,372 ±5 | 12.0% | 2026-10-02 | no-thinking |
| LMArena |
text/longer_query
|
1,373 ±2.99 | 1,375 ±3 | 6.3% | 2026-10-02 | no-thinking |
| LMArena |
text/multi_turn
|
1,366 ±3.55 | 1,368 ±3 | 6.2% | 2026-10-02 | no-thinking |
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 1,341 [1,336–1,346] Percentile 40 · #167 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,372 ±3.24 | 1,356 ±3 | 90.2% | 2026-10-02 | no-thinking |
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 1,347 [1,338–1,356] Percentile 46 · #139 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,373 ±5.46 | 1,367 ±5 | 87.7% | 2026-10-02 | no-thinking |
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 1,369 [1,363–1,375] Percentile 36 · #73 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,198 ±4.84 | 1,383 ±4 | 64.7% | 2026-10-02 | no-thinking |
| LMArena |
vision/ocr
|
1,203 ±5.87 | 1,378 ±6 | 15.4% | 2026-10-02 | no-thinking |
| LMArena |
vision/diagram
|
1,197 ±9.47 | 1,372 ±8 | 13.3% | 2026-10-02 | no-thinking |
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 1,371 [1,366–1,376] Percentile 55 · #121 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,358 ±3.85 | 1,386 ±4 | 61.9% | 2026-10-02 | no-thinking |
| LMArena |
text/longer_query
|
1,373 ±2.99 | 1,375 ±3 | 32.0% | 2026-10-02 | no-thinking |
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 1,366 [1,359–1,374] Percentile 44 · #126 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,404 ±5.09 | 1,377 ±4 | 93.7% | 2026-10-02 | no-thinking |
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 1,378 [1,362–1,395] Percentile 43 · #82 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,390 ±10 | 1,393 ±9 | 92.2% | 2026-10-02 | no-thinking |
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 1,360 [1,355–1,365] Percentile 50 · #138 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,383 ±2.44 | 1,370 ±3 | 94.0% | 2026-10-02 | no-thinking |
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 1,381 [1,367–1,395] Percentile 34 · #98 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,396 ±8.20 | 1,395 ±8 | 92.7% | 2026-10-02 | no-thinking |
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 1,362 [1,344–1,379] Percentile 26 · #100 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,388 ±11 | 1,376 ±10 | 91.8% | 2026-10-02 | no-thinking |
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 1,380 [1,362–1,398] Percentile 42 · #74 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,359 ±13 | 1,396 ±10 | 91.7% | 2026-10-02 | no-thinking |
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: 한국어 1,384 [1,370–1,399] Percentile 42 · #79 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,353 ±11 | 1,399 ±8 | 92.5% | 2026-10-02 | no-thinking |
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 1,370 [1,359–1,381] Percentile 26 · #97 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,370 ±7.29 | 1,382 ±6 | 93.2% | 2026-10-02 | no-thinking |
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 1,371 [1,364–1,378] Percentile 46 · #126 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,373 ±4.27 | 1,382 ±4 | 93.8% | 2026-10-02 | no-thinking |
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-lite-preview-09-2025-no-thinking | 1,355 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.