DeepSeek V4.1 Flash 1017 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
A 1,452 ±15
Percentile 88 · #37 · provisional
People prefer / Solves tasks
— / 1,476
Human votes vs benchmarks, Elo-eq
Value
+100
$0.486 per 1M tokens, median of 77 providers · vendor $0.2625
On your hardware
Does not fit the reference setups.
Score decomposition
A General 1,452 [1,437–1,466] Percentile 88 · #37 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
159 ±1.27 | 1,512 ±10 | 73.9% | 2026-10-17 | — |
| Epoch AI |
simpleqa_verified
outlier decay ×0.58 |
0.42 ±0.02 | 1,431 ±5 | 4.6% | 2026-10-19 | max |
| Epoch AI |
gpqa_diamond
decay ×0.25 |
0.93 ±0.02 | 1,473 ±7 | 3.6% | 2026-10-19 | 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
S Coding 1,465 [1,463–1,467] Percentile 96 · #14 · components: 2
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
webdev/overall
|
1,661 ±3.42 | 1,496 ±1 | 68.2% | 2026-11-15 | max |
| Terminal-Bench |
tbench/terminal-bench
decay ×0.90 |
0.38 ±0.02 | 1,471 ±4 | 23.2% | 2026-10-17 | 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 Agents 1,441 [1,439–1,444] Percentile 74 · #21 · components: 2
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
agent/overall
|
0.01 ±0.00 | 1,461 ±1 | 68.1% | 2026-11-15 | max |
| Terminal-Bench |
tbench/terminal-bench
decay ×0.90 |
0.38 ±0.02 | 1,471 ±4 | 23.3% | 2026-10-17 | 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
A Math 1,429 [1,420–1,437] Percentile 83 · #45 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
frontiermath_t1_3
decay ×0.82 |
0.71 ±0.03 | 1,475 ±6 | 62.4% | 2026-10-19 | max |
| Epoch AI |
frontiermath_t4
decay ×0.82 |
0.46 ±0.08 | 1,466 ±13 | 21.1% | 2026-10-19 | 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 | 2026-11 |
|---|---|
| DeepSeek V4.1 Flash 1017 | 1,452 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.