Claude Opus 4.6 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
S 1,476 ±5
Percentile 98 · #6
People prefer / Solves tasks
1,492 / 1,452
Human votes vs benchmarks, Elo-eq
Value
+41
$10 per 1M tokens, median of 36 providers · vendor $10
On your hardware
Closed weights: cloud only.
Score decomposition
S General 1,476 [1,470–1,481] Percentile 98 · #6 · components: 9
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
155 ±1.00 | 1,479 ±8 | 32.9% | 2026-02-05 | — |
| LMArena |
text/overall
|
1,503 ±1.73 | 1,503 ±2 | 15.8% | 2026-10-02 | high |
| LMArena |
text/hard_prompts
|
1,527 ±2.11 | 1,509 ±2 | 15.8% | 2026-10-02 | high |
| LMArena |
text/instruction_following
|
1,524 ±2.62 | 1,530 ±2 | 7.8% | 2026-10-02 | high |
| LMArena |
text/expert
|
1,546 ±4.09 | 1,514 ±3 | 7.6% | 2026-10-02 | high |
| LMArena |
text/longer_query
|
1,520 ±2.49 | 1,512 ±2 | 3.9% | 2026-10-02 | high |
| LMArena |
text/multi_turn
|
1,513 ±3.22 | 1,502 ±3 | 3.9% | 2026-10-02 | high |
| Epoch AI |
simpleqa_verified
decay ×0.61 |
0.47 ±0.02 | 1,445 ±5 | 3.8% | 2026-08-27 | max |
| Epoch AI |
gpqa_diamond
decay ×0.26 |
0.91 ±0.02 | 1,461 ±8 | 1.5% | 2026-02-06 | 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
S Coding 1,458 [1,455–1,462] Percentile 95 · #14 · components: 3
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
webdev/overall
|
1,546 ±2.78 | 1,463 ±1 | 39.4% | 2026-10-01 | high |
| LMArena |
text/coding
|
1,535 ±2.79 | 1,501 ±2 | 38.5% | 2026-10-02 | high |
| Epoch AI |
swe_bench_verified
decay ×0.37 |
0.79 ±0.02 | 1,477 ±10 | 13.9% | 2026-02-18 | — |
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
D Agents 1,406 [1,395–1,418] Percentile 25 · #43 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| τ²-bench (Sierra) |
tau2/banking_knowledge
decay ×0.76 |
0.27 ±0.05 | 1,459 ±8 | 79.5% | 2026-05-06 | max |
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
S Math 1,464 [1,457–1,470] Percentile 96 · #11 · components: 3
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,517 ±5.04 | 1,506 ±5 | 53.0% | 2026-10-02 | high |
| Epoch AI |
frontiermath_t1_3
decay ×0.86 |
0.66 ±0.03 | 1,464 ±6 | 28.9% | 2026-06-11 | max |
| Epoch AI |
frontiermath_t4
decay ×0.86 |
0.27 ±0.07 | 1,435 ±11 | 10.8% | 2026-06-11 | max |
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 1,474 [1,470–1,478] Percentile 96 · #5 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,316 ±3.28 | 1,489 ±3 | 62.9% | 2026-10-02 | high |
| LMArena |
vision/ocr
|
1,327 ±3.20 | 1,497 ±3 | 15.7% | 2026-10-02 | — |
| LMArena |
vision/diagram
|
1,340 ±4.46 | 1,499 ±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 1,508 [1,504–1,513] Percentile 99 · #3 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,506 ±3.26 | 1,537 ±3 | 62.1% | 2026-10-02 | high |
| LMArena |
text/longer_query
|
1,520 ±2.49 | 1,512 ±2 | 31.8% | 2026-10-02 | high |
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 1,476 [1,470–1,483] Percentile 98 · #5 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,552 ±4.60 | 1,494 ±4 | 93.8% | 2026-10-02 | high |
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 1,471 [1,457–1,485] Percentile 99 · #3 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,504 ±9.03 | 1,492 ±8 | 92.6% | 2026-10-02 | high |
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 1,488 [1,484–1,493] Percentile 100 · #2 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,512 ±2.32 | 1,506 ±2 | 94.0% | 2026-10-02 | high |
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 1,480 [1,470–1,491] Percentile 99 · #2 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,510 ±6.48 | 1,501 ±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: Français 1,470 [1,458–1,482] Percentile 99 · #2 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,513 ±7.01 | 1,490 ±6 | 93.1% | 2026-10-02 | high |
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 1,467 [1,452–1,483] Percentile 93 · #10 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,484 ±11 | 1,489 ±8 | 92.4% | 2026-10-02 | high |
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 1,465 [1,453–1,477] Percentile 98 · #4 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,465 ±8.74 | 1,484 ±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
A Language: Polski 1,469 [1,457–1,482] Percentile 98 · #4 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,497 ±7.91 | 1,489 ±7 | 93.0% | 2026-10-02 | high |
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 1,476 [1,470–1,482] Percentile 97 · #8 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,497 ±3.64 | 1,494 ±3 | 93.9% | 2026-10-02 | high |
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 Opus 4.6 | 1,476 S |
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.