GPT-5.5 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
S 1,466 ±6
Percentile 96 · #13
People prefer / Solves tasks
1,460 / 1,476
Human votes vs benchmarks, Elo-eq
Value
+29
$11.25 per 1M tokens, median of 38 providers · vendor $11.25
On your hardware
Closed weights: cloud only.
Score decomposition
S General 1,466 [1,460–1,472] Percentile 96 · #13 · components: 9
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
159 ±1.43 | 1,510 ±11 | 28.6% | 2026-04-23 | — |
| LMArena |
text/overall
|
1,471 ±1.89 | 1,471 ±2 | 16.8% | 2026-10-02 | high |
| LMArena |
text/hard_prompts
|
1,489 ±2.22 | 1,475 ±2 | 16.8% | 2026-10-02 | high |
| LMArena |
text/instruction_following
|
1,478 ±2.70 | 1,487 ±3 | 8.3% | 2026-10-02 | high |
| LMArena |
text/expert
|
1,508 ±3.96 | 1,482 ±3 | 8.2% | 2026-10-02 | high |
| LMArena |
text/longer_query
|
1,484 ±2.56 | 1,479 ±2 | 4.2% | 2026-10-02 | high |
| Epoch AI |
simpleqa_verified
decay ×0.61 |
0.63 ±0.02 | 1,495 ±5 | 4.1% | 2026-08-27 | xhigh |
| LMArena |
text/multi_turn
|
1,476 ±3.42 | 1,468 ±3 | 4.1% | 2026-10-02 | high |
| Epoch AI |
gpqa_diamond
decay ×0.26 |
0.91 ±0.02 | 1,461 ±8 | 1.5% | 2026-05-05 | low |
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 1,435 [1,432–1,437] Percentile 86 · #39 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
webdev/overall
|
1,512 ±3.03 | 1,453 ±1 | 45.8% | 2026-10-01 | xhigh-codex-harness |
| LMArena |
text/coding
|
1,494 ±2.89 | 1,465 ±3 | 44.6% | 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 Agents 1,459 [1,454–1,465] Percentile 81 · #12 · components: 2
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
agent/overall
|
0.04 ±0.01 | 1,475 ±2 | 66.5% | 2026-10-02 | xhigh |
| τ²-bench (Sierra) |
tau2/banking_knowledge
decay ×0.76 |
0.45 ±0.05 | 1,488 ±8 | 26.3% | 2026-07-22 | 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
S Math 1,469 [1,462–1,475] Percentile 97 · #8 · components: 3
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,486 ±5.35 | 1,476 ±5 | 51.7% | 2026-10-02 | — |
| Epoch AI |
frontiermath_t1_3
decay ×0.86 |
0.85 ±0.02 | 1,506 ±5 | 30.5% | 2026-06-11 | xhigh |
| Epoch AI |
frontiermath_t4
decay ×0.86 |
0.72 ±0.07 | 1,508 ±11 | 10.5% | 2026-06-11 | 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 Vision 1,459 [1,455–1,463] Percentile 87 · #16 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,297 ±3.01 | 1,472 ±3 | 63.0% | 2026-10-02 | — |
| LMArena |
vision/ocr
|
1,308 ±3.02 | 1,479 ±3 | 15.7% | 2026-10-02 | — |
| LMArena |
vision/diagram
|
1,326 ±4.28 | 1,486 ±4 | 15.3% | 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 Writing 1,466 [1,461–1,470] Percentile 93 · #20 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,455 ±3.33 | 1,485 ±3 | 62.1% | 2026-10-02 | high |
| LMArena |
text/longer_query
|
1,484 ±2.56 | 1,479 ±2 | 31.8% | 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
A Language: 繁體中文 1,464 [1,456–1,471] Percentile 96 · #10 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,535 ±4.97 | 1,481 ±4 | 93.7% | 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: Deutsch 1,451 [1,436–1,467] Percentile 94 · #10 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,481 ±9.72 | 1,472 ±8 | 92.4% | 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
A Language: English 1,446 [1,442–1,451] Percentile 89 · #32 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,470 ±2.44 | 1,462 ±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 1,443 [1,431–1,455] Percentile 88 · #19 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,468 ±7.36 | 1,461 ±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 1,447 [1,436–1,459] Percentile 85 · #21 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,486 ±7.07 | 1,466 ±6 | 93.1% | 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: 日本語 1,477 [1,462–1,492] Percentile 97 · #5 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,497 ±11 | 1,499 ±8 | 92.5% | 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 1,462 [1,449–1,475] Percentile 96 · #7 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,461 ±9.38 | 1,482 ±7 | 92.9% | 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: Polski 1,444 [1,430–1,457] Percentile 85 · #20 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,465 ±8.93 | 1,462 ±8 | 92.7% | 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: Русский 1,456 [1,449–1,462] Percentile 91 · #22 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,473 ±3.91 | 1,472 ±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
History
The same in a table
| Model | 2026-10 |
|---|---|
| GPT-5.5 | 1,466 S |
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.