Skip to content
fedi.software

Claude Opus 4 (Search) in fedi-index

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

fedi-index · General

B 1,376 ±5

Percentile 53 · #141

People prefer / Solves tasks

1,382 / 1,368

Human votes vs benchmarks, Elo-eq

Value

-103

$30 per 1M tokens, median of 6 providers

On your hardware

Closed weights: cloud only.

Score decomposition

B General 1,376 [1,370–1,381] Percentile 53 · #141 · components: 8
Source Component Value Elo-eq Weight Measured Variant
Epoch AI eci 143 ±0.81 1,382 ±6 39.9% 2025-05-22 —
LMArena text/overall 1,377 ±2.27 1,377 ±2 15.3% 2026-11-11 thinking-16k-20250514
LMArena text/hard_prompts 1,400 ±2.89 1,394 ±3 15.2% 2026-11-11 thinking-16k-20250514
LMArena text/instruction_following 1,406 ±3.51 1,419 ±3 7.5% 2026-11-11 thinking-16k-20250514
LMArena text/expert 1,385 ±7.29 1,383 ±6 6.8% 2026-11-11 thinking-16k-20250514
LMArena text/longer_query 1,422 ±3.91 1,421 ±4 3.7% 2026-11-11 thinking-16k-20250514
LMArena text/multi_turn 1,396 ±4.20 1,395 ±4 3.7% 2026-11-11 thinking-16k-20250514
Epoch AI gpqa_diamond decay ×0.25 0.76 ±0.03 1,394 ±14 1.0% 2025-05-22 16k

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 Coding 1,399 [1,393–1,405] Percentile 64 · #104 · components: 2
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,442 ±4.01 1,419 ±4 78.1% 2026-11-11 thinking-16k-20250514
Epoch AI swe_bench_verified decay ×0.35 0.71 ±0.02 1,436 ±11 11.6% 2026-02-06 —

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 Math 1,361 [1,351–1,371] Percentile 46 · #140 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,390 ±6.26 1,384 ±6 87.3% 2026-11-11 thinking-16k-20250514

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 Vision 1,364 [1,352–1,375] Percentile 29 · #79 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena vision/overall 1,192 ±8.16 1,377 ±7 76.2% 2026-11-09 thinking-16k-20250514
LMArena vision/ocr 1,197 ±10 1,372 ±10 16.5% 2026-11-09 thinking-16k-20250514

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 Search 1,356 [1,351–1,362] Percentile 0 · #36 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena search/overall 1,127 ±2.80 1,366 ±3 93.9% 2026-11-09 search

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 Writing 1,403 [1,397–1,410] Percentile 65 · #94 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,386 ±4.73 1,415 ±5 61.6% 2026-11-11 thinking-16k-20250514
LMArena text/longer_query 1,422 ±3.91 1,421 ±4 32.1% 2026-11-11 thinking-16k-20250514

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 Language: 繁體中文 1,352 [1,343–1,362] Percentile 38 · #136 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,386 ±6.30 1,363 ±5 93.5% 2026-11-11 thinking-16k-20250514

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 Language: Deutsch 1,379 [1,363–1,395] Percentile 43 · #83 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/german 1,390 ±10 1,394 ±9 92.3% 2026-11-11 thinking-16k-20250514

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 Language: English 1,363 [1,357–1,368] Percentile 49 · #137 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,386 ±2.94 1,373 ±3 93.9% 2026-11-11 thinking-16k-20250514

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 Language: Español 1,373 [1,356–1,391] Percentile 26 · #112 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/spanish 1,389 ±10 1,388 ±10 91.9% 2026-11-11 thinking-16k-20250514

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 Language: Français 1,347 [1,325–1,369] Percentile 19 · #115 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/french 1,373 ±14 1,362 ±12 90.4% 2026-11-11 thinking-16k-20250514

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 Language: 日本語 1,362 [1,347–1,378] Percentile 31 · #88 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/japanese 1,331 ±11 1,376 ±8 92.4% 2026-11-11 thinking-16k-20250514

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 Language: 한국어 1,362 [1,346–1,377] Percentile 31 · #95 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/korean 1,320 ±11 1,375 ±9 92.4% 2026-11-11 thinking-16k-20250514

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 Language: Polski 1,359 [1,350–1,368] Percentile 18 · #108 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/polish 1,356 ±5.59 1,370 ±5 93.6% 2026-11-11 thinking-16k-20250514

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 1,386 [1,377–1,396] Percentile 52 · #112 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,392 ±5.86 1,399 ±5 93.4% 2026-11-11 thinking-16k-20250514

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 2026-11
Claude Opus 4 (Search) 1,376 B

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 (Search)

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