GPT-5.2 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
A 1,428 ±5
Percentile 82 · #53
People prefer / Solves tasks
1,421 / 1,438
Human votes vs benchmarks, Elo-eq
Value
+12
$4.81 per 1M tokens, median of 26 providers · vendor $4.81
On your hardware
Closed weights: cloud only.
Score decomposition
A General 1,428 [1,423–1,434] Percentile 82 · #53 · components: 9
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
153 ±0.97 | 1,465 ±8 | 33.4% | 2025-12-11 | — |
| LMArena |
text/overall
|
1,439 ±2.04 | 1,439 ±2 | 15.8% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,445 ±2.50 | 1,435 ±2 | 15.7% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,417 ±3.16 | 1,429 ±3 | 7.7% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,445 ±4.93 | 1,431 ±4 | 7.5% | 2026-10-02 | high |
| Epoch AI |
simpleqa_verified
decay ×0.61 |
0.37 ±0.02 | 1,414 ±5 | 3.9% | 2026-08-27 | xhigh |
| LMArena |
text/longer_query
|
1,428 ±3.05 | 1,427 ±3 | 3.9% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,458 ±3.96 | 1,452 ±4 | 3.8% | 2026-10-02 | — |
| Epoch AI |
gpqa_diamond
decay ×0.26 |
0.91 ±0.02 | 1,465 ±8 | 1.4% | 2025-12-13 | xhigh |
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 1,409 [1,405–1,414] Percentile 73 · #76 · components: 3
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,447 ±3.42 | 1,423 ±3 | 39.0% | 2026-10-02 | — |
| LMArena |
webdev/overall
|
1,415 ±11 | 1,426 ±3 | 38.8% | 2026-10-01 | — |
| Epoch AI |
swe_bench_verified
decay ×0.37 |
0.74 ±0.02 | 1,452 ±10 | 13.7% | 2026-02-12 | 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
C Agents 1,412 [1,400–1,425] Percentile 32 · #40 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| τ²-bench (Sierra) |
tau2/banking_knowledge
decay ×0.76 |
0.32 ±0.05 | 1,467 ±8 | 79.2% | 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
A Math 1,426 [1,419–1,433] Percentile 84 · #43 · components: 3
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,439 ±5.49 | 1,431 ±5 | 52.7% | 2026-10-02 | high |
| Epoch AI |
frontiermath_t1_3
decay ×0.86 |
0.67 ±0.03 | 1,467 ±6 | 29.3% | 2026-06-11 | xhigh |
| Epoch AI |
frontiermath_t4
decay ×0.86 |
0.32 ±0.07 | 1,443 ±12 | 10.6% | 2026-06-11 | xhigh |
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 1,432 [1,428–1,436] Percentile 68 · #37 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,268 ±3.32 | 1,446 ±3 | 63.1% | 2026-10-02 | — |
| LMArena |
vision/ocr
|
1,275 ±3.44 | 1,447 ±3 | 15.6% | 2026-10-02 | — |
| LMArena |
vision/diagram
|
1,285 ±5.11 | 1,450 ±4 | 15.0% | 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 Writing 1,415 [1,410–1,421] Percentile 73 · #74 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,402 ±4.28 | 1,430 ±4 | 61.5% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,428 ±3.05 | 1,427 ±3 | 32.2% | 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 Language: 繁體中文 1,407 [1,398–1,416] Percentile 62 · #86 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,460 ±6.31 | 1,421 ±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
B Language: Deutsch 1,422 [1,402–1,442] Percentile 72 · #41 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,448 ±13 | 1,443 ±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
B Language: English 1,422 [1,417–1,428] Percentile 75 · #70 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,446 ±2.81 | 1,436 ±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
B Language: Español 1,412 [1,397–1,427] Percentile 57 · #65 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,433 ±9.08 | 1,429 ±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: Français 1,421 [1,406–1,435] Percentile 65 · #48 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,456 ±8.68 | 1,438 ±8 | 92.6% | 2026-10-02 | 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 Language: 日本語 1,421 [1,400–1,441] Percentile 72 · #36 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,420 ±15 | 1,442 ±11 | 91.1% | 2026-10-02 | 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 Language: 한국어 1,409 [1,391–1,427] Percentile 62 · #53 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,390 ±13 | 1,428 ±10 | 91.7% | 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: Polski 1,417 [1,400–1,434] Percentile 60 · #53 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,434 ±11 | 1,436 ±10 | 91.9% | 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 1,428 [1,420–1,435] Percentile 78 · #51 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,440 ±4.72 | 1,443 ±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 |
|---|---|
| GPT-5.2 | 1,428 A |
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.