GPT-5.1 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
A 1,426 ±4
Percentile 82 · #55
People prefer / Solves tasks
1,432 / 1,418
Human votes vs benchmarks, Elo-eq
Value
+18
$3.44 per 1M tokens, median of 26 providers · vendor $3.44
On your hardware
Closed weights: cloud only.
Score decomposition
A General 1,426 [1,422–1,430] Percentile 82 · #55 · components: 9
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
150 ±0.72 | 1,435 ±6 | 35.7% | 2025-11-13 | — |
| LMArena |
text/overall
|
1,443 ±1.88 | 1,443 ±2 | 15.3% | 2026-10-02 | high |
| LMArena |
text/hard_prompts
|
1,457 ±2.45 | 1,446 ±2 | 15.2% | 2026-10-02 | high |
| LMArena |
text/instruction_following
|
1,443 ±3.20 | 1,454 ±3 | 7.5% | 2026-10-02 | high |
| LMArena |
text/expert
|
1,470 ±6.01 | 1,452 ±5 | 7.0% | 2026-10-02 | high |
| LMArena |
text/longer_query
|
1,448 ±3.22 | 1,445 ±3 | 3.7% | 2026-10-02 | high |
| Epoch AI |
simpleqa_verified
decay ×0.61 |
0.48 ±0.02 | 1,448 ±5 | 3.7% | 2026-08-27 | high |
| LMArena |
text/multi_turn
|
1,450 ±3.83 | 1,444 ±4 | 3.7% | 2026-10-02 | high |
| Epoch AI |
gpqa_diamond
decay ×0.26 |
0.88 ±0.02 | 1,447 ±9 | 1.3% | 2025-11-13 | 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 Coding 1,405 [1,402–1,409] Percentile 70 · #84 · components: 3
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
webdev/overall
|
1,395 ±5.86 | 1,420 ±2 | 39.9% | 2026-10-01 | medium |
| LMArena |
text/coding
|
1,454 ±3.51 | 1,429 ±3 | 38.7% | 2026-10-02 | high |
| Epoch AI |
swe_bench_verified
decay ×0.37 |
0.68 ±0.02 | 1,422 ±11 | 13.0% | 2026-02-18 | 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 1,408 [1,398–1,418] Percentile 76 · #62 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,446 ±5.91 | 1,438 ±6 | 87.5% | 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
B Vision 1,415 [1,410–1,420] Percentile 56 · #50 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,250 ±3.98 | 1,429 ±4 | 63.5% | 2026-10-02 | high |
| LMArena |
vision/ocr
|
1,255 ±4.47 | 1,428 ±4 | 15.5% | 2026-10-02 | high |
| LMArena |
vision/diagram
|
1,265 ±6.41 | 1,432 ±6 | 14.7% | 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 Writing 1,437 [1,431–1,442] Percentile 81 · #51 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,427 ±4.10 | 1,456 ±4 | 61.8% | 2026-10-02 | high |
| LMArena |
text/longer_query
|
1,448 ±3.22 | 1,445 ±3 | 32.0% | 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: 繁體中文 1,434 [1,426–1,441] Percentile 81 · #44 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,495 ±5.26 | 1,449 ±4 | 93.7% | 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
B Language: Deutsch 1,417 [1,400–1,434] Percentile 66 · #49 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,439 ±11 | 1,436 ±10 | 91.9% | 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
B Language: English 1,427 [1,422–1,432] Percentile 79 · #57 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,451 ±2.74 | 1,442 ±3 | 93.9% | 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
B Language: Español 1,410 [1,395–1,425] Percentile 53 · #71 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,431 ±8.85 | 1,427 ±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
B Language: Français 1,415 [1,398–1,432] Percentile 57 · #59 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,450 ±10 | 1,433 ±9 | 92.0% | 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: 日本語 1,444 [1,425–1,463] Percentile 87 · #18 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,453 ±14 | 1,466 ±11 | 91.4% | 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
B Language: 한국어 1,418 [1,401–1,434] Percentile 67 · #45 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,401 ±12 | 1,436 ±9 | 92.2% | 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
B Language: Polski 1,424 [1,411–1,438] Percentile 68 · #42 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,440 ±8.62 | 1,442 ±7 | 92.8% | 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
B Language: Русский 1,424 [1,417–1,431] Percentile 76 · #58 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,435 ±4.22 | 1,439 ±4 | 93.8% | 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
History
The same in a table
| Model | 2026-10 |
|---|---|
| GPT-5.1 | 1,426 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.