Claude Opus 5 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
S 1,493 ±7
Percentile 99 · #3
People prefer / Solves tasks
1,492 / 1,494
Human votes vs benchmarks, Elo-eq
Value
+59
$10 per 1M tokens, median of 29 providers · vendor $10
On your hardware
Closed weights: cloud only.
Score decomposition
S General 1,493 [1,486–1,500] Percentile 99 · #3 · components: 9
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
163 ±1.62 | 1,539 ±13 | 26.9% | 2026-07-24 | — |
| LMArena |
text/overall
|
1,507 ±2.52 | 1,507 ±2 | 17.2% | 2026-10-02 | max |
| LMArena |
text/hard_prompts
|
1,526 ±2.92 | 1,509 ±3 | 17.2% | 2026-10-02 | max |
| LMArena |
text/instruction_following
|
1,516 ±3.56 | 1,523 ±3 | 8.4% | 2026-10-02 | max |
| LMArena |
text/expert
|
1,559 ±4.29 | 1,524 ±4 | 8.4% | 2026-10-02 | high |
| Epoch AI |
simpleqa_verified
decay ×0.61 |
0.60 ±0.02 | 1,486 ±5 | 4.3% | 2026-08-10 | max |
| LMArena |
text/longer_query
|
1,514 ±3.30 | 1,507 ±3 | 4.2% | 2026-10-02 | max |
| LMArena |
text/multi_turn
|
1,500 ±4.88 | 1,489 ±4 | 4.1% | 2026-10-02 | max |
| Epoch AI |
gpqa_diamond
decay ×0.26 |
0.94 ±0.01 | 1,476 ±7 | 1.7% | 2026-07-24 | 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 1,474 [1,471–1,477] Percentile 99 · #5 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
webdev/overall
|
1,695 ±3.30 | 1,505 ±1 | 46.3% | 2026-10-01 | max |
| LMArena |
text/coding
|
1,534 ±3.95 | 1,500 ±4 | 44.0% | 2026-10-02 | 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 Agents 1,475 [1,469–1,481] Percentile 93 · #5 · components: 2
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
agent/overall
|
0.09 ±0.01 | 1,497 ±3 | 66.1% | 2026-10-02 | high |
| τ²-bench (Sierra) |
tau2/banking_knowledge
decay ×0.76 |
0.49 ±0.05 | 1,495 ±8 | 26.7% | 2026-08-03 | 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 1,489 [1,481–1,498] Percentile 99 · #4 · components: 3
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,531 ±8.33 | 1,519 ±8 | 48.2% | 2026-10-02 | max |
| Epoch AI |
frontiermath_t1_3
decay ×0.86 |
0.86 ±0.02 | 1,506 ±4 | 32.6% | 2026-07-24 | max |
| Epoch AI |
frontiermath_t4
decay ×0.86 |
0.73 ±0.07 | 1,509 ±11 | 11.5% | 2026-07-24 | 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 1,479 [1,475–1,483] Percentile 99 · #2 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,321 ±3.49 | 1,494 ±3 | 63.1% | 2026-10-02 | high |
| LMArena |
vision/ocr
|
1,330 ±3.65 | 1,500 ±4 | 15.6% | 2026-10-02 | high |
| LMArena |
vision/diagram
|
1,350 ±5.22 | 1,508 ±5 | 15.0% | 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 Writing 1,497 [1,491–1,502] Percentile 98 · #6 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,491 ±4.38 | 1,521 ±4 | 61.6% | 2026-10-02 | max |
| LMArena |
text/longer_query
|
1,514 ±3.30 | 1,507 ±3 | 32.2% | 2026-10-02 | 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 Language: 繁體中文 1,493 [1,483–1,503] Percentile 99 · #3 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,576 ±6.84 | 1,514 ±5 | 93.4% | 2026-10-02 | 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 Language: Deutsch 1,482 [1,460–1,503] Percentile 100 · #1 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,525 ±14 | 1,510 ±12 | 90.6% | 2026-10-02 | 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 Language: English 1,480 [1,474–1,487] Percentile 99 · #4 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,505 ±3.31 | 1,499 ±4 | 93.8% | 2026-10-02 | 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 Language: Español 1,482 [1,463–1,500] Percentile 100 · #1 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,517 ±11 | 1,507 ±10 | 91.6% | 2026-10-02 | 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 Language: Français 1,474 [1,461–1,488] Percentile 100 · #1 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,519 ±8.10 | 1,496 ±7 | 92.8% | 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: 日本語 1,488 [1,472–1,503] Percentile 100 · #1 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,513 ±11 | 1,512 ±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 1,499 [1,482–1,517] Percentile 100 · #1 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,519 ±13 | 1,526 ±10 | 91.8% | 2026-10-02 | 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 Language: Polski 1,483 [1,462–1,505] Percentile 99 · #2 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,524 ±14 | 1,512 ±12 | 90.7% | 2026-10-02 | 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 Language: Русский 1,484 [1,475–1,493] Percentile 98 · #5 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,508 ±5.42 | 1,504 ±5 | 93.5% | 2026-10-02 | 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
History
The same in a table
| Model | 2026-10 |
|---|---|
| Claude Opus 5 | 1,493 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.