DeepSeek-V2.5 (1210) in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
C 1,284 ±5
Percentile 33 · #199 · provisional
People prefer / Solves tasks
1,289 / —
Human votes vs benchmarks, Elo-eq
Value
—
On your hardware
Closed weights: cloud only.
Score decomposition
C General 1,284 [1,279–1,288] Percentile 33 · #199 · components: 6 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,294 ±4.19 | 1,294 ±4 | 27.4% | 2026-11-11 | 1210 |
| LMArena |
text/hard_prompts
|
1,289 ±6.74 | 1,295 ±6 | 25.4% | 2026-11-11 | 1210 |
| LMArena |
text/instruction_following
|
1,279 ±5.69 | 1,299 ±5 | 13.1% | 2026-11-11 | 1210 |
| LMArena |
text/expert
|
1,266 ±13 | 1,285 ±11 | 9.7% | 2026-11-11 | 1210 |
| LMArena |
text/multi_turn
|
1,297 ±8.31 | 1,305 ±8 | 5.9% | 2026-11-11 | 1210 |
| LMArena |
text/longer_query
|
1,301 ±8.73 | 1,308 ±8 | 5.7% | 2026-11-11 | 1210 |
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 Coding 1,287 [1,274–1,300] Percentile 31 · #198 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,309 ±8.54 | 1,300 ±8 | 86.4% | 2026-11-11 | 1210 |
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 Math 1,275 [1,261–1,288] Percentile 33 · #171 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,288 ±8.48 | 1,286 ±8 | 86.1% | 2026-11-11 | 1210 |
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 Writing 1,302 [1,290–1,313] Percentile 40 · #160 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,285 ±8.77 | 1,311 ±9 | 60.6% | 2026-11-11 | 1210 |
| LMArena |
text/longer_query
|
1,301 ±8.73 | 1,308 ±8 | 31.7% | 2026-11-11 | 1210 |
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 Language: 繁體中文 1,300 [1,281–1,318] Percentile 30 · #154 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,318 ±13 | 1,308 ±10 | 91.5% | 2026-11-11 | 1210 |
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 Language: English 1,287 [1,276–1,297] Percentile 36 · #173 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,310 ±5.26 | 1,292 ±6 | 93.4% | 2026-11-11 | 1210 |
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 Language: 한국어 1,282 [1,259–1,305] Percentile 16 · #115 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,210 ±17 | 1,291 ±13 | 90.2% | 2026-11-11 | — |
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
C Language: Русский 1,300 [1,285–1,314] Percentile 31 · #159 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,289 ±8.82 | 1,307 ±8 | 92.6% | 2026-11-11 | 1210 |
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-V2.5 (1210) | 1,284 C |
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.