Gemini 2.5 Pro in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
B 1,413 ±5
Percentile 76 · #72
People prefer / Solves tasks
1,433 / 1,387
Human votes vs benchmarks, Elo-eq
Value
+5
$3.44 per 1M tokens, median of 28 providers · vendor $3.44
On your hardware
Closed weights: cloud only.
Score decomposition
B General 1,413 [1,408–1,418] Percentile 76 · #72 · components: 8
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
145 ±0.77 | 1,401 ±6 | 39.3% | 2025-06-05 | — |
| LMArena |
text/overall
|
1,458 ±1.24 | 1,458 ±1 | 15.1% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,455 ±1.59 | 1,444 ±1 | 15.1% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,436 ±1.95 | 1,447 ±2 | 7.5% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,452 ±3.46 | 1,437 ±3 | 7.4% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,449 ±2.00 | 1,446 ±2 | 3.8% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,453 ±2.39 | 1,447 ±2 | 3.7% | 2026-10-02 | — |
| Epoch AI |
gpqa_diamond
decay ×0.26 |
0.85 ±0.02 | 1,436 ±10 | 1.4% | 2025-11-16 | — |
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 1,367 [1,363–1,372] Percentile 52 · #135 · components: 3
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
webdev/overall
|
1,227 ±8.07 | 1,372 ±2 | 49.2% | 2026-10-01 | — |
| LMArena |
text/coding
outlier |
1,452 ±2.15 | 1,427 ±2 | 24.8% | 2026-10-02 | — |
| Epoch AI |
swe_bench_verified
decay ×0.37 |
0.58 ±0.02 | 1,368 ±12 | 15.6% | 2026-02-13 | — |
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 Agents 1,392 [1,382–1,401] Percentile 10 · #52 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| τ²-bench (Sierra) |
tau2/banking_knowledge
decay ×0.76 |
0.14 ±0.03 | 1,436 ±6 | 80.9% | 2026-05-05 | 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 Math 1,400 [1,395–1,404] Percentile 70 · #76 · components: 3
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,450 ±3.52 | 1,441 ±3 | 50.9% | 2026-10-02 | — |
| Epoch AI |
frontiermath_t1_3
decay ×0.86 |
0.25 ±0.03 | 1,374 ±6 | 27.1% | 2026-06-11 | — |
| Epoch AI |
frontiermath_t4
decay ×0.86 |
0.00 ±0.00 | 1,393 ±0 | 15.4% | 2026-06-11 | — |
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 1,427 [1,424–1,430] Percentile 63 · #42 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,263 ±2.32 | 1,442 ±2 | 63.0% | 2026-10-02 | — |
| LMArena |
vision/ocr
|
1,270 ±2.44 | 1,443 ±2 | 15.7% | 2026-10-02 | — |
| LMArena |
vision/diagram
|
1,274 ±3.58 | 1,440 ±3 | 15.4% | 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
A Writing 1,455 [1,451–1,458] Percentile 88 · #33 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,454 ±2.59 | 1,483 ±3 | 62.3% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,449 ±2.00 | 1,446 ±2 | 31.6% | 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
A Language: 繁體中文 1,444 [1,439–1,449] Percentile 86 · #33 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,508 ±3.41 | 1,459 ±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
A Language: Deutsch 1,458 [1,448–1,469] Percentile 95 · #8 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,486 ±6.41 | 1,477 ±6 | 93.4% | 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
A Language: English 1,435 [1,431–1,438] Percentile 86 · #40 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,458 ±1.69 | 1,449 ±2 | 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
A Language: Español 1,450 [1,440–1,459] Percentile 93 · #12 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,474 ±5.66 | 1,467 ±5 | 93.4% | 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: Français 1,436 [1,424–1,447] Percentile 78 · #30 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,472 ±6.81 | 1,453 ±6 | 93.2% | 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
A Language: 日本語 1,455 [1,444–1,465] Percentile 88 · #16 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,462 ±7.52 | 1,473 ±6 | 93.4% | 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
A Language: 한국어 1,444 [1,435–1,454] Percentile 88 · #17 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,434 ±6.66 | 1,461 ±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
A Language: Polski 1,457 [1,451–1,464] Percentile 91 · #13 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,479 ±4.29 | 1,474 ±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
A Language: Русский 1,446 [1,441–1,450] Percentile 87 · #31 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,461 ±2.88 | 1,461 ±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
History
The same in a table
| Model | 2026-10 |
|---|---|
| Gemini 2.5 Pro | 1,413 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.