Skip to content
fedi.software

Claude Opus 4.7 in fedi-index

The score in every slice, what it is made of, value, local run and history.

fedi-index · General

S 1,469 ±5

Percentile 97 · #10

People prefer / Solves tasks

1,476 / 1,460

Human votes vs benchmarks, Elo-eq

Value

+35

$10 per 1M tokens, median of 38 providers · vendor $10

On your hardware

Closed weights: cloud only.

Score decomposition

S General 1,469 [1,464–1,475] Percentile 97 · #10 · components: 9
Source Component Value Elo-eq Weight Measured Variant
Epoch AI eci 156 ±1.02 1,487 ±8 32.8% 2026-04-16 —
LMArena text/overall 1,490 ±1.91 1,490 ±2 15.8% 2026-10-02 high
LMArena text/hard_prompts 1,506 ±2.27 1,490 ±2 15.8% 2026-10-02 high
LMArena text/instruction_following 1,498 ±2.77 1,506 ±3 7.8% 2026-10-02 high
LMArena text/expert 1,520 ±4.10 1,493 ±3 7.7% 2026-10-02 —
LMArena text/longer_query 1,505 ±2.63 1,499 ±2 3.9% 2026-10-02 high
Epoch AI simpleqa_verified decay ×0.61 0.52 ±0.02 1,460 ±5 3.9% 2026-08-27 xhigh
LMArena text/multi_turn 1,505 ±3.50 1,495 ±3 3.8% 2026-10-02 high
Epoch AI gpqa_diamond decay ×0.26 0.90 ±0.02 1,459 ±9 1.4% 2026-04-17 xhigh

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 1,458 [1,454–1,461] Percentile 95 · #16 · components: 3
Source Component Value Elo-eq Weight Measured Variant
LMArena webdev/overall 1,557 ±2.94 1,466 ±1 39.2% 2026-10-01 high
LMArena text/coding 1,518 ±2.97 1,487 ±3 38.1% 2026-10-02 high
Epoch AI swe_bench_verified decay ×0.37 0.83 ±0.02 1,502 ±9 14.5% 2026-04-20 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

C Agents 1,422 [1,409–1,435] Percentile 37 · #37 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
τ²-bench (Sierra) tau2/banking_knowledge decay ×0.76 0.40 ±0.05 1,481 ±8 78.8% 2026-07-23 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 Math 1,458 [1,451–1,464] Percentile 94 · #17 · components: 3
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,499 ±5.48 1,488 ±5 52.6% 2026-10-02 high
Epoch AI frontiermath_t1_3 decay ×0.86 0.70 ±0.03 1,473 ±6 29.4% 2026-06-10 max
Epoch AI frontiermath_t4 decay ×0.86 0.32 ±0.07 1,443 ±12 10.5% 2026-06-10 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 · #6 · components: 3 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena vision/overall 1,316 ±3.36 1,490 ±3 63.0% 2026-10-02 —
LMArena vision/ocr 1,326 ±3.39 1,496 ±3 15.6% 2026-10-02 —
LMArena vision/diagram 1,336 ±4.64 1,495 ±4 15.2% 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 Search 1,460 [1,454–1,465] Percentile 91 · #4 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena search/overall 1,233 ±2.75 1,476 ±3 93.9% 2026-08-24 —

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 1,492 [1,487–1,496] Percentile 97 · #8 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,486 ±3.52 1,516 ±4 62.0% 2026-10-02 high
LMArena text/longer_query 1,505 ±2.63 1,499 ±2 31.9% 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

A Language: 繁體中文 1,461 [1,454–1,468] Percentile 95 · #12 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,531 ±5.04 1,478 ±4 93.7% 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: Deutsch 1,463 [1,448–1,478] Percentile 98 · #4 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/german 1,496 ±9.70 1,485 ±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: English 1,472 [1,467–1,477] Percentile 97 · #9 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,496 ±2.50 1,490 ±3 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 1,467 [1,454–1,479] Percentile 97 · #5 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/spanish 1,495 ±7.37 1,487 ±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: Français 1,464 [1,451–1,476] Percentile 97 · #5 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/french 1,505 ±7.34 1,483 ±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: 日本語 1,457 [1,440–1,474] Percentile 90 · #14 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/japanese 1,470 ±12 1,479 ±9 92.0% 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: 한국어 1,464 [1,451–1,477] Percentile 97 · #5 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/korean 1,464 ±9.56 1,484 ±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

A Language: Polski 1,463 [1,449–1,477] Percentile 93 · #10 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/polish 1,490 ±9.08 1,483 ±8 92.7% 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 1,473 [1,467–1,480] Percentile 96 · #10 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,494 ±4.09 1,491 ±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

History

fedi-index by month
The same in a table
Model 2026-10
Claude Opus 4.7 1,469 S

Badge

Show the model's fedi-index on your site or in a README. The badge updates itself; it links to this page.

fedi-index: Claude Opus 4.7

Data CC BY 4.0: keep the link to fedi.software.