Skip to content
fedi.software

Claude 3 Sonnet (20240229) in fedi-index

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

fedi-index · General

D 1,211 ±9

Percentile 23 · #228

People prefer / Solves tasks

1,217 / 1,199

Human votes vs benchmarks, Elo-eq

Value

-218

$6 per 1M tokens, median of 1 providers

On your hardware

Closed weights: cloud only.

Score decomposition

D General 1,211 [1,202–1,220] Percentile 23 · #228 · components: 8
Source Component Value Elo-eq Weight Measured Variant
Epoch AI eci 119 ±2.07 1,197 ±16 26.2% 2024-02-29 —
LMArena text/overall 1,218 ±2.02 1,218 ±2 18.7% 2026-11-11 —
LMArena text/hard_prompts 1,197 ±3.01 1,211 ±3 18.4% 2026-11-11 —
LMArena text/instruction_following 1,199 ±2.86 1,223 ±3 9.2% 2026-11-11 —
LMArena text/expert 1,172 ±6.02 1,208 ±5 8.6% 2026-11-11 —
LMArena text/multi_turn 1,227 ±4.05 1,242 ±4 4.5% 2026-11-11 —
LMArena text/longer_query 1,211 ±4.39 1,224 ±4 4.4% 2026-11-11 —
Epoch AI gpqa_diamond decay ×0.25 0.41 ±0.02 1,229 ±11 1.5% 2025-01-27 —

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 Coding 1,221 [1,215–1,226] Percentile 23 · #220 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,223 ±3.71 1,223 ±3 88.4% 2026-11-11 —

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 Math 1,213 [1,206–1,220] Percentile 25 · #193 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,213 ±4.11 1,214 ±4 88.2% 2026-11-11 —

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 Vision 1,190 [1,180–1,200] Percentile 9 · #101 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena vision/overall 984 ±5.83 1,189 ±5 93.4% 2026-11-09 —

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 Writing 1,214 [1,208–1,220] Percentile 24 · #201 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,186 ±4.19 1,210 ±4 62.3% 2026-11-11 —
LMArena text/longer_query 1,211 ±4.39 1,224 ±4 31.4% 2026-11-11 —

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: 繁體中文 1,206 [1,199–1,213] Percentile 15 · #186 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,189 ±4.73 1,206 ±4 93.8% 2026-11-11 —

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: Deutsch 1,231 [1,218–1,243] Percentile 15 · #124 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/german 1,204 ±7.79 1,233 ±7 93.0% 2026-11-11 —

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 1,204 [1,199–1,209] Percentile 26 · #199 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,226 ±2.49 1,204 ±3 94.0% 2026-11-11 —

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: Español 1,216 [1,198–1,235] Percentile 6 · #141 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/spanish 1,204 ±11 1,217 ±10 91.6% 2026-11-11 —

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 1,228 [1,210–1,245] Percentile 8 · #130 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/french 1,229 ±11 1,230 ±10 91.8% 2026-11-11 —

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: 日本語 1,224 [1,212–1,237] Percentile 6 · #120 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/japanese 1,131 ±9.36 1,226 ±7 92.9% 2026-11-11 —

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: 한국어 1,227 [1,213–1,240] Percentile 6 · #129 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/korean 1,128 ±9.96 1,229 ±8 92.7% 2026-11-11 —

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: Русский 1,248 [1,240–1,256] Percentile 19 · #186 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,226 ±4.64 1,251 ±4 93.7% 2026-11-11 —

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 3 Sonnet (20240229) 1,211 D

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 3 Sonnet (20240229)

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