Claude Opus 4.5 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
A 1,436 ±6
Percentile 85 · #46
People prefer / Solves tasks
1,448 / 1,417
Human votes vs benchmarks, Elo-eq
Value
+2
$10 per 1M tokens, median of 34 providers · vendor $10
On your hardware
Closed weights: cloud only.
Score decomposition
A General 1,436 [1,430–1,442] Percentile 85 · #46 · components: 9
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
150 ±1.21 | 1,438 ±10 | 30.9% | 2025-11-24 | — |
| LMArena |
text/overall
|
1,451 ±1.59 | 1,451 ±2 | 16.4% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,476 ±2.01 | 1,463 ±2 | 16.3% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,477 ±3.38 | 1,486 ±3 | 7.9% | 2026-10-02 | high-32k |
| LMArena |
text/expert
|
1,487 ±4.22 | 1,466 ±4 | 7.9% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,480 ±2.51 | 1,475 ±2 | 4.0% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,466 ±3.06 | 1,459 ±3 | 4.0% | 2026-10-02 | — |
| Epoch AI |
simpleqa_verified
decay ×0.61 |
0.46 ±0.02 | 1,441 ±5 | 4.0% | 2026-08-27 | 32k |
| Epoch AI |
gpqa_diamond
decay ×0.26 |
0.86 ±0.02 | 1,440 ±10 | 1.4% | 2025-11-24 | 32k |
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 1,440 [1,436–1,443] Percentile 90 · #28 · components: 3
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
webdev/overall
|
1,493 ±4.21 | 1,448 ±1 | 39.7% | 2026-10-01 | high-32k |
| LMArena |
text/coding
|
1,503 ±3.66 | 1,473 ±3 | 38.2% | 2026-10-02 | high-32k |
| Epoch AI |
swe_bench_verified
decay ×0.37 |
0.77 ±0.02 | 1,466 ±10 | 13.8% | 2026-02-05 | — |
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 Agents 1,404 [1,392–1,415] Percentile 21 · #46 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| τ²-bench (Sierra) |
tau2/banking_knowledge
decay ×0.76 |
0.25 ±0.04 | 1,455 ±7 | 79.7% | 2026-05-05 | 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
B Math 1,411 [1,404–1,418] Percentile 78 · #58 · components: 3
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,462 ±6.18 | 1,453 ±6 | 49.8% | 2026-10-02 | high-32k |
| Epoch AI |
frontiermath_t1_3
decay ×0.86 |
0.34 ±0.03 | 1,396 ±6 | 28.4% | 2026-06-11 | 32k |
| Epoch AI |
frontiermath_t4
decay ×0.86 |
0.05 ±0.03 | 1,400 ±5 | 14.6% | 2026-06-11 | 32k |
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 1,458 [1,452–1,463] Percentile 91 · #25 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,445 ±4.21 | 1,474 ±4 | 61.4% | 2026-10-02 | high-32k |
| LMArena |
text/longer_query
|
1,480 ±2.51 | 1,475 ±2 | 32.4% | 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
B Language: 繁體中文 1,416 [1,409–1,422] Percentile 70 · #68 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,470 ±4.35 | 1,430 ±4 | 93.8% | 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
B Language: Deutsch 1,427 [1,412–1,441] Percentile 76 · #35 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,449 ±9.29 | 1,445 ±8 | 92.6% | 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: English 1,437 [1,433–1,441] Percentile 87 · #37 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,461 ±2.22 | 1,452 ±2 | 94.0% | 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
B Language: Español 1,432 [1,417–1,448] Percentile 78 · #33 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,457 ±9.07 | 1,451 ±8 | 92.4% | 2026-10-02 | high-32k |
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: Français 1,434 [1,422–1,446] Percentile 76 · #33 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,471 ±7.47 | 1,452 ±7 | 93.0% | 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
B Language: 日本語 1,416 [1,394–1,437] Percentile 67 · #43 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,415 ±16 | 1,438 ±12 | 90.6% | 2026-10-02 | high-32k |
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 1,436 [1,423–1,449] Percentile 82 · #25 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,425 ±9.31 | 1,454 ±7 | 92.9% | 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
B Language: Polski 1,425 [1,414–1,435] Percentile 71 · #39 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,439 ±6.93 | 1,441 ±6 | 93.3% | 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 1,435 [1,429–1,440] Percentile 82 · #44 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,448 ±3.44 | 1,450 ±3 | 93.9% | 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
History
The same in a table
| Model | 2026-10 |
|---|---|
| Claude Opus 4.5 | 1,436 A |
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.