Qwen3.8 Max (0902) in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
A 1,459 ±5
Percentile 94 · #19
People prefer / Solves tasks
1,465 / 1,451
Human votes vs benchmarks, Elo-eq
Value
+54
$3 per 1M tokens, median of 29 providers · vendor $3
On your hardware
Closed weights: cloud only.
Score decomposition
A General 1,459 [1,454–1,465] Percentile 94 · #19 · components: 9
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
155 ±0.99 | 1,478 ±8 | 33.5% | 2026-09-01 | — |
| LMArena |
text/overall
|
1,482 ±2.65 | 1,482 ±3 | 15.8% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,495 ±3.03 | 1,481 ±3 | 15.7% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,479 ±3.70 | 1,488 ±4 | 7.7% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,507 ±5.96 | 1,482 ±5 | 7.4% | 2026-10-02 | — |
| Epoch AI |
simpleqa_verified
decay ×0.61 |
0.47 ±0.02 | 1,446 ±5 | 3.9% | 2026-09-02 | xhigh |
| LMArena |
text/longer_query
|
1,487 ±3.53 | 1,482 ±3 | 3.9% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,488 ±5.26 | 1,479 ±5 | 3.7% | 2026-10-02 | — |
| Epoch AI |
gpqa_diamond
decay ×0.26 |
0.92 ±0.02 | 1,469 ±8 | 1.5% | 2026-09-02 | xhigh |
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 Coding 1,458 [1,454–1,462] Percentile 95 · #15 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
webdev/overall
|
1,671 ±6.15 | 1,498 ±2 | 46.1% | 2026-10-01 | — |
| LMArena |
text/coding
|
1,502 ±4.06 | 1,472 ±4 | 44.2% | 2026-10-02 | — |
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 1,442 [1,440–1,445] Percentile 61 · #23 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
agent/overall
|
0.03 ±0.00 | 1,468 ±2 | 90.5% | 2026-10-02 | — |
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 1,453 [1,444–1,462] Percentile 92 · #21 · components: 3
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,500 ±8.90 | 1,489 ±8 | 48.7% | 2026-10-02 | — |
| Epoch AI |
frontiermath_t1_3
decay ×0.86 |
0.66 ±0.03 | 1,463 ±6 | 31.9% | 2026-09-02 | xhigh |
| Epoch AI |
frontiermath_t4
decay ×0.86 |
0.34 ±0.07 | 1,447 ±12 | 11.4% | 2026-09-02 | xhigh |
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 Vision 1,470 [1,466–1,475] Percentile 94 · #8 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,314 ±3.81 | 1,488 ±3 | 63.4% | 2026-10-02 | — |
| LMArena |
vision/ocr
|
1,323 ±4.04 | 1,494 ±4 | 15.6% | 2026-10-02 | — |
| LMArena |
vision/diagram
|
1,324 ±6.24 | 1,485 ±6 | 14.7% | 2026-10-02 | — |
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 Writing 1,480 [1,474–1,486] Percentile 96 · #11 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,478 ±4.91 | 1,508 ±5 | 61.2% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,487 ±3.53 | 1,482 ±3 | 32.4% | 2026-10-02 | — |
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 Language: 繁體中文 1,465 [1,454–1,476] Percentile 96 · #9 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,538 ±7.53 | 1,484 ±6 | 93.2% | 2026-10-02 | — |
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 Language: Deutsch 1,449 [1,426–1,472] Percentile 92 · #13 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,486 ±15 | 1,476 ±13 | 90.1% | 2026-10-02 | — |
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 Language: English 1,468 [1,460–1,474] Percentile 96 · #11 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,492 ±3.56 | 1,485 ±4 | 93.8% | 2026-10-02 | — |
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 Language: Español 1,463 [1,444–1,483] Percentile 96 · #7 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,497 ±12 | 1,488 ±11 | 91.3% | 2026-10-02 | — |
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 Language: Français 1,458 [1,439–1,476] Percentile 95 · #8 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,503 ±11 | 1,481 ±10 | 91.6% | 2026-10-02 | — |
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 Language: 日本語 1,452 [1,430–1,473] Percentile 87 · #17 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,468 ±16 | 1,477 ±12 | 90.6% | 2026-10-02 | — |
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 Language: 한국어 1,460 [1,441–1,480] Percentile 94 · #9 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,465 ±14 | 1,485 ±11 | 91.4% | 2026-10-02 | — |
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 Language: Polski 1,446 [1,422–1,469] Percentile 88 · #16 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,477 ±16 | 1,473 ±13 | 89.9% | 2026-10-02 | — |
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 Language: Русский 1,460 [1,451–1,470] Percentile 92 · #19 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,480 ±5.69 | 1,478 ±5 | 93.5% | 2026-10-02 | — |
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 |
|---|---|
| Qwen3.8 Max (0902) | 1,459 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.