Claude Sonnet 4.6 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
A 1,443 ±6
Percentile 88 · #35
People prefer / Solves tasks
1,453 / 1,428
Human votes vs benchmarks, Elo-eq
Value
+21
$6 per 1M tokens, median of 42 providers · vendor $6
On your hardware
Closed weights: cloud only.
Score decomposition
A General 1,443 [1,437–1,449] Percentile 88 · #35 · components: 9
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
152 ±1.17 | 1,455 ±9 | 31.3% | 2026-02-17 | — |
| LMArena |
text/overall
|
1,458 ±1.79 | 1,458 ±2 | 16.2% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,484 ±2.17 | 1,471 ±2 | 16.2% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,475 ±2.64 | 1,484 ±2 | 8.0% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,500 ±3.99 | 1,476 ±3 | 7.8% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,479 ±2.53 | 1,474 ±2 | 4.0% | 2026-10-02 | — |
| Epoch AI |
simpleqa_verified
decay ×0.61 |
0.36 ±0.02 | 1,409 ±5 | 4.0% | 2026-08-10 | high |
| LMArena |
text/multi_turn
|
1,464 ±3.27 | 1,457 ±3 | 4.0% | 2026-10-02 | — |
| Epoch AI |
gpqa_diamond
decay ×0.26 |
0.87 ±0.02 | 1,446 ±9 | 1.4% | 2026-02-20 | 32k |
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 1,442 [1,439–1,446] Percentile 92 · #23 · components: 3
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
webdev/overall
|
1,522 ±2.62 | 1,456 ±1 | 39.6% | 2026-10-06 | — |
| LMArena |
text/coding
|
1,504 ±2.83 | 1,474 ±2 | 38.6% | 2026-10-02 | — |
| Epoch AI |
swe_bench_verified
decay ×0.37 |
0.75 ±0.02 | 1,459 ±10 | 13.5% | 2026-02-21 | — |
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 1,423 [1,415–1,432] Percentile 83 · #44 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,463 ±5.12 | 1,454 ±5 | 87.8% | 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 Vision 1,446 [1,442–1,450] Percentile 80 · #23 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,283 ±3.14 | 1,459 ±3 | 62.9% | 2026-10-02 | — |
| LMArena |
vision/ocr
|
1,296 ±3.13 | 1,467 ±3 | 15.7% | 2026-10-02 | — |
| LMArena |
vision/diagram
|
1,305 ±4.33 | 1,468 ±4 | 15.3% | 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 Writing 1,452 [1,447–1,456] Percentile 86 · #37 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,435 ±3.33 | 1,464 ±3 | 62.1% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,479 ±2.53 | 1,474 ±2 | 31.8% | 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
B Language: 繁體中文 1,431 [1,424–1,438] Percentile 78 · #49 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,491 ±4.83 | 1,446 ±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
B Language: Deutsch 1,410 [1,396–1,424] Percentile 63 · #54 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,428 ±9.11 | 1,426 ±8 | 92.6% | 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 1,448 [1,444–1,453] Percentile 89 · #31 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,472 ±2.39 | 1,464 ±2 | 94.0% | 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 1,440 [1,428–1,452] Percentile 84 · #25 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,464 ±7.08 | 1,457 ±7 | 93.1% | 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
B Language: Français 1,430 [1,418–1,442] Percentile 72 · #39 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,465 ±7.23 | 1,447 ±7 | 93.0% | 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 1,423 [1,407–1,438] Percentile 75 · #33 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,419 ±11 | 1,441 ±9 | 92.3% | 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
B Language: 한국어 1,426 [1,413–1,440] Percentile 74 · #36 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,411 ±9.52 | 1,444 ±7 | 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
B Language: Polski 1,426 [1,414–1,439] Percentile 72 · #37 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,442 ±8.07 | 1,443 ±7 | 93.0% | 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 1,428 [1,422–1,434] Percentile 79 · #50 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,440 ±3.76 | 1,443 ±3 | 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
History
The same in a table
| Model | 2026-10 |
|---|---|
| Claude Sonnet 4.6 | 1,443 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.