DeepSeek V4 Pro 0813 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
A 1,435 ±11
Percentile 84 · #47 · provisional
People prefer / Solves tasks
— / 1,454
Human votes vs benchmarks, Elo-eq
Value
+40
$1.98 per 1M tokens, median of 34 providers · vendor $0.99
On your hardware
Does not fit the reference setups.
Score decomposition
A General 1,435 [1,423–1,446] Percentile 84 · #47 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
155 ±1.01 | 1,480 ±8 | 72.6% | 2026-08-13 | — |
| Epoch AI |
simpleqa_verified
decay ×0.61 |
0.53 ±0.02 | 1,464 ±5 | 8.5% | 2026-08-27 | max |
| Epoch AI |
gpqa_diamond
decay ×0.26 |
0.92 ±0.02 | 1,466 ±7 | 3.4% | 2026-08-18 | max |
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 1,415 [1,406–1,424] Percentile 80 · #53 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
frontiermath_t1_3
decay ×0.86 |
0.65 ±0.03 | 1,461 ±6 | 61.4% | 2026-08-19 | max |
| Epoch AI |
frontiermath_t4
decay ×0.86 |
0.27 ±0.07 | 1,435 ±11 | 23.0% | 2026-08-19 | max |
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 |
|---|---|
| DeepSeek V4 Pro 0813 | 1,435 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.