Gemini 3.1 Flash Lite Preview in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
B 1,380 ±2
Percentile 58 · #124 · provisional
People prefer / Solves tasks
1,391 / —
Human votes vs benchmarks, Elo-eq
Value
+16
$0.5625 per 1M tokens, median of 12 providers · vendor $0.5625
On your hardware
Closed weights: cloud only.
Score decomposition
B General 1,380 [1,379–1,382] Percentile 58 · #124 · components: 6 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,416 ±1.85 | 1,416 ±2 | 25.6% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,407 ±2.27 | 1,401 ±2 | 25.5% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,376 ±2.72 | 1,391 ±3 | 12.6% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,397 ±4.20 | 1,392 ±3 | 12.3% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,394 ±2.65 | 1,395 ±2 | 6.3% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,417 ±3.29 | 1,414 ±3 | 6.2% | 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 [1,361–1,366] Percentile 50 · #141 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
webdev/overall
|
1,256 ±3.47 | 1,380 ±1 | 45.8% | 2026-10-01 | — |
| LMArena |
text/coding
|
1,400 ±2.92 | 1,381 ±3 | 44.6% | 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 Math 1,393 [1,385–1,402] Percentile 65 · #89 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,427 ±5.14 | 1,420 ±5 | 87.8% | 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
C Vision 1,406 [1,402–1,409] Percentile 49 · #58 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,240 ±2.95 | 1,421 ±3 | 63.0% | 2026-10-02 | — |
| LMArena |
vision/ocr
|
1,246 ±2.97 | 1,419 ±3 | 15.7% | 2026-10-02 | — |
| LMArena |
vision/diagram
|
1,242 ±4.30 | 1,412 ±4 | 15.2% | 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 Writing 1,404 [1,400–1,409] Percentile 66 · #93 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,401 ±3.49 | 1,429 ±4 | 62.0% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,394 ±2.65 | 1,395 ±2 | 31.9% | 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: 繁體中文 1,408 [1,401–1,416] Percentile 63 · #83 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,461 ±4.94 | 1,422 ±4 | 93.7% | 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 Language: Deutsch 1,410 [1,395–1,425] Percentile 64 · #53 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,429 ±9.69 | 1,427 ±8 | 92.4% | 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 1,390 [1,386–1,395] Percentile 60 · #111 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,414 ±2.46 | 1,402 ±3 | 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
C Language: Español 1,402 [1,390–1,415] Percentile 49 · #77 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,420 ±7.13 | 1,417 ±7 | 93.1% | 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
C Language: Français 1,394 [1,381–1,406] Percentile 42 · #79 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,423 ±7.47 | 1,408 ±7 | 93.0% | 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: 日本語 1,417 [1,400–1,434] Percentile 68 · #41 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,412 ±13 | 1,436 ±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: 한국어 1,413 [1,400–1,427] Percentile 64 · #50 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,393 ±9.82 | 1,430 ±8 | 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
B Language: Polski 1,427 [1,414–1,440] Percentile 73 · #36 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,443 ±8.40 | 1,444 ±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 1,411 [1,405–1,417] Percentile 67 · #78 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,420 ±3.84 | 1,425 ±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
History
The same in a table
| Model | 2026-10 |
|---|---|
| Gemini 3.1 Flash Lite Preview | 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.