Claude Opus 5.5 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
S 1,504 ±8
Percentile 100 · #1
People prefer / Solves tasks
1,496 / 1,520
Human votes vs benchmarks, Elo-eq
Value
+76◆
$8 per 1M tokens, median of 25 providers · vendor $8
On your hardware
Closed weights: cloud only.
Score decomposition
S General 1,504 [1,496–1,513] Percentile 100 · #1 · components: 9
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
167 ±1.94 | 1,574 ±15 | 26.1% | 2026-09-22 | — |
| LMArena |
text/overall
|
1,512 ±4.62 | 1,512 ±5 | 18.6% | 2026-10-02 | high |
| LMArena |
text/hard_prompts
|
1,535 ±5.75 | 1,517 ±5 | 18.2% | 2026-10-02 | high |
| LMArena |
text/instruction_following
|
1,534 ±7.74 | 1,540 ±7 | 8.2% | 2026-10-02 | high |
| LMArena |
text/expert
|
1,551 ±13 | 1,518 ±11 | 6.6% | 2026-10-02 | high |
| Epoch AI |
simpleqa_verified
decay ×0.61 |
0.72 ±0.01 | 1,524 ±4 | 5.0% | 2026-09-22 | max |
| LMArena |
text/longer_query
|
1,534 ±7.13 | 1,526 ±7 | 4.2% | 2026-10-02 | high |
| LMArena |
text/multi_turn
|
1,501 ±12 | 1,491 ±11 | 3.2% | 2026-10-02 | high |
| Epoch AI |
gpqa_diamond
outlier decay ×0.26 |
0.91 ±0.02 | 1,461 ±9 | 0.9% | 2026-09-22 | 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 Coding 1,489 [1,482–1,495] Percentile 100 · #1 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
webdev/overall
|
1,815 ±8.20 | 1,539 ±2 | 49.8% | 2026-10-01 | max |
| LMArena |
text/coding
|
1,535 ±9.04 | 1,502 ±8 | 39.6% | 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 Agents 1,488 [1,479–1,497] Percentile 98 · #2 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
agent/overall
|
0.14 ±0.01 | 1,522 ±5 | 89.5% | 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 Math 1,482 [1,477–1,488] Percentile 98 · #5 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
frontiermath_t1_3
decay ×0.86 |
0.91 ±0.02 | 1,519 ±4 | 59.7% | 2026-09-22 | max |
| Epoch AI |
frontiermath_t4
decay ×0.86 |
0.95 ±0.04 | 1,544 ±7 | 26.5% | 2026-09-22 | 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 Writing 1,522 [1,510–1,534] Percentile 100 · #2 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,532 ±10 | 1,563 ±10 | 57.2% | 2026-10-02 | high |
| LMArena |
text/longer_query
|
1,534 ±7.13 | 1,526 ±7 | 35.0% | 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: 繁體中文 1,490 [1,469–1,512] Percentile 99 · #4 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,583 ±15 | 1,520 ±12 | 90.8% | 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: English 1,485 [1,471–1,499] Percentile 99 · #3 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,513 ±7.22 | 1,507 ±8 | 92.7% | 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 1,478 [1,458–1,497] Percentile 97 · #7 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,507 ±12 | 1,503 ±11 | 91.4% | 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
History
The same in a table
| Model | 2026-10 |
|---|---|
| Claude Opus 5.5 | 1,504 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.