LongCat-Flash-Chat Exp (2602) in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
B 1,402 ±2
Percentile 66 · #102 · provisional
People prefer / Solves tasks
1,414 / —
Human votes vs benchmarks, Elo-eq
Value
—
On your hardware
Closed weights: cloud only.
Score decomposition
B General 1,402 [1,399–1,404] Percentile 66 · #102 · components: 6 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,426 ±2.29 | 1,426 ±2 | 25.8% | 2026-11-11 | 2602 |
| LMArena |
text/hard_prompts
|
1,439 ±2.77 | 1,430 ±2 | 25.7% | 2026-11-11 | 2602 |
| LMArena |
text/instruction_following
|
1,411 ±3.44 | 1,424 ±3 | 12.6% | 2026-11-11 | 2602 |
| LMArena |
text/expert
|
1,454 ±5.84 | 1,438 ±5 | 12.0% | 2026-11-11 | 2602 |
| LMArena |
text/longer_query
|
1,425 ±3.32 | 1,423 ±3 | 6.3% | 2026-11-11 | 2602 |
| LMArena |
text/multi_turn
|
1,417 ±4.43 | 1,415 ±4 | 6.2% | 2026-11-11 | 2602 |
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 1,416 [1,410–1,422] Percentile 74 · #76 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,470 ±3.69 | 1,444 ±3 | 88.4% | 2026-11-11 | 2602 |
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 1,396 [1,378–1,414] Percentile 64 · #93 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,441 ±11 | 1,432 ±11 | 84.2% | 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
B Writing 1,405 [1,399–1,411] Percentile 65 · #92 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,388 ±4.77 | 1,416 ±5 | 61.2% | 2026-11-11 | 2602 |
| LMArena |
text/longer_query
|
1,425 ±3.32 | 1,423 ±3 | 32.4% | 2026-11-11 | 2602 |
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 1,410 [1,400–1,420] Percentile 62 · #84 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,464 ±6.98 | 1,424 ±6 | 93.4% | 2026-11-11 | 2602 |
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 1,427 [1,421–1,433] Percentile 78 · #59 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,451 ±3.01 | 1,441 ±3 | 93.9% | 2026-11-11 | 2602 |
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 1,415 [1,390–1,440] Percentile 56 · #67 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,445 ±15 | 1,440 ±14 | 89.4% | 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: 한국어 1,395 [1,376–1,414] Percentile 48 · #72 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,370 ±14 | 1,413 ±10 | 91.6% | 2026-11-11 | 2602 |
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: Polski 1,395 [1,377–1,412] Percentile 38 · #81 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,405 ±12 | 1,412 ±10 | 91.8% | 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
B Language: Русский 1,387 [1,371–1,404] Percentile 52 · #111 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,396 ±9.95 | 1,403 ±9 | 92.2% | 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
History
The same in a table
| Model | 2026-11 |
|---|---|
| LongCat-Flash-Chat Exp (2602) | 1,402 B |
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.