gemini-pro-dev-api in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
D 1,147 ±4
Percentile 18 · #241 · provisional
People prefer / Solves tasks
1,144 / —
Human votes vs benchmarks, Elo-eq
Value
—
On your hardware
Closed weights: cloud only.
Score decomposition
D General 1,147 [1,143–1,151] Percentile 18 · #241 · components: 6 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,149 ±3.67 | 1,149 ±4 | 27.1% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,109 ±5.70 | 1,132 ±5 | 25.7% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,114 ±5.33 | 1,142 ±5 | 12.9% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,059 ±12 | 1,116 ±10 | 10.2% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,124 ±7.40 | 1,149 ±7 | 6.0% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,132 ±8.98 | 1,150 ±8 | 5.5% | 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
D Coding 1,127 [1,116–1,138] Percentile 13 · #242 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,104 ±7.01 | 1,117 ±6 | 89.1% | 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 Math 1,145 [1,133–1,156] Percentile 16 · #215 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,132 ±7.06 | 1,136 ±7 | 86.9% | 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 Writing 1,156 [1,146–1,166] Percentile 19 · #218 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,130 ±7.04 | 1,153 ±7 | 63.1% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,132 ±8.98 | 1,150 ±8 | 29.6% | 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: 繁體中文 1,158 [1,145–1,171] Percentile 12 · #196 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,124 ±8.85 | 1,155 ±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
D Language: Deutsch 1,168 [1,145–1,192] Percentile 13 · #126 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,124 ±15 | 1,165 ±13 | 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
D Language: English 1,141 [1,132–1,149] Percentile 19 · #221 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,162 ±4.28 | 1,136 ±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
D Language: Français 1,158 [1,131–1,184] Percentile 6 · #127 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,144 ±17 | 1,152 ±15 | 88.7% | 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
D Language: Русский 1,214 [1,197–1,230] Percentile 15 · #200 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,186 ±10 | 1,214 ±9 | 92.1% | 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
History
The same in a table
| Model | 2026-10 |
|---|---|
| gemini-pro-dev-api | 1,147 D |
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.