Claude 3 Opus (20240229) in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
C 1,254 ±7
Percentile 29 · #212
People prefer / Solves tasks
1,258 / 1,246
Human votes vs benchmarks, Elo-eq
Value
-225
$30 per 1M tokens, median of 1 providers
On your hardware
Closed weights: cloud only.
Score decomposition
C General 1,254 [1,247–1,260] Percentile 29 · #212 · components: 9
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
126 ±1.48 | 1,245 ±12 | 28.9% | 2024-02-29 | — |
| LMArena |
text/overall
|
1,262 ±1.55 | 1,262 ±2 | 17.5% | 2026-11-11 | — |
| LMArena |
text/hard_prompts
|
1,245 ±2.45 | 1,255 ±2 | 17.3% | 2026-11-11 | — |
| LMArena |
text/instruction_following
|
1,248 ±2.29 | 1,269 ±2 | 8.6% | 2026-11-11 | — |
| LMArena |
text/expert
|
1,222 ±4.76 | 1,249 ±4 | 8.3% | 2026-11-11 | — |
| LMArena |
text/multi_turn
|
1,275 ±3.14 | 1,286 ±3 | 4.3% | 2026-11-11 | — |
| LMArena |
text/longer_query
|
1,259 ±3.25 | 1,269 ±3 | 4.2% | 2026-11-11 | — |
| Epoch AI |
simpleqa_verified
outlier decay ×0.58 |
0.13 ±0.01 | 1,337 ±3 | 2.1% | 2026-08-31 | — |
| Epoch AI |
gpqa_diamond
decay ×0.25 |
0.47 ±0.03 | 1,259 ±12 | 1.2% | 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
C Coding 1,254 [1,249–1,258] Percentile 27 · #210 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,264 ±2.98 | 1,260 ±3 | 88.6% | 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
C Math 1,263 [1,258–1,268] Percentile 32 · #175 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,273 ±3.31 | 1,271 ±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 Vision 1,223 [1,214–1,232] Percentile 14 · #95 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,023 ±5.29 | 1,224 ±5 | 93.6% | 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
C Writing 1,259 [1,254–1,263] Percentile 32 · #181 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,235 ±3.32 | 1,260 ±3 | 62.4% | 2026-11-11 | — |
| LMArena |
text/longer_query
|
1,259 ±3.25 | 1,269 ±3 | 31.5% | 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 1,250 [1,244–1,256] Percentile 24 · #166 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,248 ±4.09 | 1,253 ±3 | 93.9% | 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: Deutsch 1,275 [1,264–1,285] Percentile 20 · #116 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,258 ±6.54 | 1,280 ±6 | 93.3% | 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 1,241 [1,237–1,245] Percentile 30 · #190 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,263 ±2.03 | 1,243 ±2 | 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 1,252 [1,236–1,268] Percentile 9 · #137 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,246 ±9.72 | 1,256 ±9 | 92.2% | 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 Language: Français 1,267 [1,251–1,283] Percentile 11 · #127 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,275 ±9.63 | 1,272 ±9 | 92.2% | 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 Language: 日本語 1,275 [1,265–1,285] Percentile 15 · #108 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,204 ±7.41 | 1,280 ±6 | 93.4% | 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: 한국어 1,269 [1,257–1,281] Percentile 12 · #120 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,188 ±8.76 | 1,274 ±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
D Language: Polski 1,341 [1,307–1,376] Percentile 13 · #114 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,352 ±24 | 1,366 ±21 | 84.7% | 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
C Language: Русский 1,293 [1,287–1,299] Percentile 29 · #164 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,280 ±3.52 | 1,299 ±3 | 93.9% | 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
History
The same in a table
| Model | 2026-11 |
|---|---|
| Claude 3 Opus (20240229) | 1,254 C |
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.