Qwen3 235B A22B Thinking 2507 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
B 1,389 ±5
Percentile 62 · #112
People prefer / Solves tasks
1,398 / 1,378
Human votes vs benchmarks, Elo-eq
Value
+12
$0.975 per 1M tokens, median of 11 providers
On your hardware
Closed weights: cloud only.
Score decomposition
B General 1,389 [1,383–1,394] Percentile 62 · #112 · components: 9
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
144 ±0.86 | 1,389 ±7 | 36.6% | 2025-07-25 | — |
| LMArena |
text/overall
|
1,415 ±3.34 | 1,415 ±3 | 16.0% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,416 ±4.83 | 1,409 ±4 | 15.5% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,385 ±6.36 | 1,399 ±6 | 7.2% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,460 ±14 | 1,444 ±12 | 5.2% | 2026-10-02 | — |
| Epoch AI |
simpleqa_verified
decay ×0.61 |
0.40 ±0.02 | 1,424 ±5 | 4.0% | 2026-08-27 | — |
| LMArena |
text/longer_query
|
1,399 ±7.25 | 1,399 ±7 | 3.5% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,407 ±8.01 | 1,405 ±7 | 3.4% | 2026-10-02 | — |
| Epoch AI |
gpqa_diamond
decay ×0.26 |
0.80 ±0.03 | 1,412 ±12 | 1.2% | 2025-12-11 | — |
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 Coding 1,381 [1,369–1,392] Percentile 57 · #119 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,424 ±7.51 | 1,403 ±7 | 88.9% | 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
B Math 1,370 [1,351–1,390] Percentile 53 · #120 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,412 ±13 | 1,405 ±12 | 82.9% | 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
B Writing 1,392 [1,380–1,404] Percentile 61 · #104 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,384 ±9.10 | 1,412 ±9 | 58.7% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,399 ±7.25 | 1,399 ±7 | 33.7% | 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
B Language: 繁體中文 1,419 [1,400–1,438] Percentile 72 · #64 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,482 ±13 | 1,439 ±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
B Language: English 1,405 [1,396–1,414] Percentile 65 · #96 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,429 ±4.82 | 1,419 ±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
B Language: 日本語 1,398 [1,378–1,418] Percentile 51 · #63 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,387 ±15 | 1,417 ±11 | 91.1% | 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
C Language: Polski 1,383 [1,367–1,399] Percentile 33 · #88 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,390 ±11 | 1,398 ±9 | 92.2% | 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 Language: Русский 1,389 [1,370–1,409] Percentile 56 · #104 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,400 ±12 | 1,407 ±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
History
The same in a table
| Model | 2026-10 |
|---|---|
| Qwen3 235B A22B Thinking 2507 | 1,389 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.