Qwen3.7 Max in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
A 1,449 ±7
Percentile 90 · #29
People prefer / Solves tasks
1,453 / 1,444
Human votes vs benchmarks, Elo-eq
Value
+39
$3.75 per 1M tokens, median of 27 providers · vendor $3.75
On your hardware
Closed weights: cloud only.
Score decomposition
A General 1,449 [1,442–1,456] Percentile 90 · #29 · components: 9
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
154 ±1.06 | 1,467 ±8 | 35.7% | 2026-05-19 | — |
| LMArena |
text/overall
|
1,476 ±4.94 | 1,476 ±5 | 16.1% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,483 ±6.02 | 1,469 ±5 | 15.8% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,460 ±8.32 | 1,470 ±8 | 7.0% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,488 ±16 | 1,466 ±13 | 5.2% | 2026-10-02 | — |
| Epoch AI |
simpleqa_verified
decay ×0.61 |
0.56 ±0.02 | 1,472 ±5 | 4.3% | 2026-08-27 | — |
| LMArena |
text/longer_query
|
1,483 ±7.72 | 1,478 ±7 | 3.6% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,481 ±12 | 1,473 ±10 | 3.0% | 2026-10-02 | — |
| Epoch AI |
gpqa_diamond
decay ×0.26 |
0.91 ±0.02 | 1,463 ±10 | 1.5% | 2026-08-07 | — |
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 1,438 [1,432–1,444] Percentile 88 · #33 · components: 3
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
webdev/overall
|
1,515 ±3.75 | 1,454 ±1 | 42.9% | 2026-10-01 | — |
| LMArena |
text/coding
|
1,497 ±9.16 | 1,468 ±8 | 33.2% | 2026-10-02 | — |
| Epoch AI |
swe_bench_verified
decay ×0.37 |
0.77 ±0.02 | 1,470 ±10 | 14.9% | 2026-06-18 | — |
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 Agents 1,409 [1,405–1,413] Percentile 30 · #41 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
agent/overall
|
-0.05 ±0.00 | 1,431 ±2 | 90.4% | 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 Math 1,417 [1,408–1,426] Percentile 82 · #48 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
frontiermath_t1_3
decay ×0.86 |
0.65 ±0.03 | 1,461 ±6 | 62.1% | 2026-06-13 | — |
| Epoch AI |
frontiermath_t4
decay ×0.86 |
0.34 ±0.07 | 1,447 ±12 | 22.2% | 2026-06-13 | — |
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 1,454 [1,439–1,469] Percentile 88 · #34 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,451 ±14 | 1,480 ±14 | 51.8% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,483 ±7.72 | 1,478 ±7 | 39.2% | 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: 繁體中文 1,450 [1,426–1,475] Percentile 89 · #25 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,533 ±18 | 1,479 ±14 | 89.6% | 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: English 1,444 [1,430–1,457] Percentile 88 · #34 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,470 ±7.06 | 1,462 ±8 | 92.8% | 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: Русский 1,451 [1,426–1,476] Percentile 89 · #26 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,482 ±16 | 1,480 ±14 | 89.4% | 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
History
The same in a table
| Model | 2026-10 |
|---|---|
| Qwen3.7 Max | 1,449 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.