GPT-5.3-Codex in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
A 1,430 ±25
Percentile 82 · #52 · provisional
People prefer / Solves tasks
— / 1,457
Human votes vs benchmarks, Elo-eq
Value
+14
$4.81 per 1M tokens, median of 24 providers · vendor $4.81
On your hardware
Closed weights: cloud only.
Score decomposition
A General 1,430 [1,406–1,455] Percentile 82 · #52 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
157 ±2.03 | 1,491 ±16 | 78.9% | 2026-02-05 | — |
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 1,402 [1,398–1,405] Percentile 68 · #89 · components: 2
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
webdev/overall
|
1,371 ±5.76 | 1,413 ±2 | 78.3% | 2026-10-01 | codex-harness |
| Epoch AI |
swe_bench_verified
decay ×0.37 |
0.75 ±0.02 | 1,457 ±10 | 13.4% | 2026-02-25 | 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
History
The same in a table
| Model | 2026-10 |
|---|---|
| GPT-5.3-Codex | 1,430 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.