gemini-1.5-flash-002 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
C 1,268 ±9
Percentile 30 · #207
People prefer / Solves tasks
1,270 / 1,265
Human votes vs benchmarks, Elo-eq
Value
—
On your hardware
Closed weights: cloud only.
Score decomposition
C General 1,268 [1,260–1,277] Percentile 30 · #207 · components: 8
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
129 ±2.06 | 1,275 ±16 | 26.4% | 2024-09-24 | — |
| LMArena |
text/overall
|
1,287 ±2.14 | 1,287 ±2 | 18.7% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,257 ±3.39 | 1,266 ±3 | 18.4% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,258 ±2.99 | 1,278 ±3 | 9.2% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,233 ±6.67 | 1,258 ±6 | 8.5% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,253 ±4.23 | 1,265 ±4 | 4.5% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,284 ±4.28 | 1,292 ±4 | 4.5% | 2026-10-02 | — |
| Epoch AI |
gpqa_diamond
decay ×0.26 |
0.47 ±0.03 | 1,260 ±13 | 1.5% | 2025-01-27 | — |
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 1,252 [1,246–1,259] Percentile 27 · #203 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,262 ±4.07 | 1,258 ±4 | 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
C Math 1,260 [1,253–1,267] Percentile 30 · #178 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,269 ±4.40 | 1,268 ±4 | 88.1% | 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
D Vision 1,322 [1,314–1,331] Percentile 21 · #89 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,141 ±5.07 | 1,331 ±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
C Writing 1,298 [1,292–1,304] Percentile 37 · #170 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,285 ±4.54 | 1,311 ±5 | 62.0% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,284 ±4.28 | 1,292 ±4 | 31.7% | 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
C Language: 繁體中文 1,285 [1,276–1,293] Percentile 25 · #167 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,295 ±5.84 | 1,290 ±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
D Language: Deutsch 1,276 [1,259–1,293] Percentile 22 · #112 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,262 ±11 | 1,283 ±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: English 1,266 [1,261–1,272] Percentile 31 · #188 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,289 ±2.76 | 1,270 ±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
D Language: 日本語 1,308 [1,293–1,323] Percentile 21 · #101 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,252 ±11 | 1,316 ±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
D Language: 한국어 1,290 [1,270–1,310] Percentile 17 · #113 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,220 ±15 | 1,299 ±11 | 91.2% | 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: Русский 1,299 [1,292–1,307] Percentile 29 · #166 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,288 ±4.50 | 1,306 ±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
History
The same in a table
| Model | 2026-10 |
|---|---|
| gemini-1.5-flash-002 | 1,268 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.