geekradar
Int
Explore GeekRadar

More to explore

Good gear All topics About us Say hello
GeekRadar / The comparison desk
COMPARE.
AI models
openai

GPT-5.1

AI model Released

API mode
Chat*
Context window
400,000 tokens
Maximum output
128,000 tokens
Open weights
No

Capability & preference

General capability · ECI

A cross-benchmark capability estimate. Index points, not a percentage; intervals show uncertainty.

GPT-5.1 149.9* GPT-5.1 · 95% interval 148.5–151.6

Human preference · Arena

Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.

GPT-5.1 1422.2 GPT-5.1 · 95% interval 1418.6–1425.7 · 44,413 votes · 2026-10-28

Model performance

Radar task score: four tests, equal weight. An experimental summary of these tasks, not a universal intelligence rating.

GPT-5.1

Radar task score

Unrated

2/4 core tests · not enough evidence

3 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

Expert-written science questions; strict multiple-choice scoring. Chance accuracy is 25%.

GPT-5.1 87.6*% Approx. 95% interval: 84.0–91.3% · Older result

Novel problem solving

Mystery Game Puzzles · 25%

Best-next-move puzzles in an undisclosed game variant. A narrow reasoning test, not general intelligence.

GPT-5.1 Not available

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

Private v2 mathematics problems with Python tools. Earlier versions and Tier 4 are excluded.

GPT-5.1 Not available

Factual answers

SimpleQA Verified · 25%

Correct factual answers under a guessing prompt, graded by a model. Not a hallucination or abstention score.

GPT-5.1 48.0*% Approx. 95% interval: 44.9–51.1%

Competition mathematics

OTIS Mock AIME 2024-2025 · Separate result

Competition problems with model-extracted answers checked against an exact key. Earlier grading procedures are excluded.

GPT-5.1 88.6*% Approx. 95% interval: 80.7–96.5% · Older result

Bars show reported task scores. Whiskers are approximate 95% intervals where standard errors are available. Different reasoning budgets are not equal-cost tests. Missing results are never zero.

Recorded results

Only the same benchmark, version, workload, scenario and unit share a row. Missing results are not zero. System results include the full submitted hardware and software configuration.

Arena text preference / chinesehuman preference · 2026-10-28 · rating

GPT-5.1

1,495.01 rating

Confidence interval: 1,484.71 – 1,505.31

3427 votes

Category
chinese
Evaluated configuration
GPT-5.1 (High)
Evaluation type
human preference

1,466.09 rating

Confidence interval: 1,456.07 – 1,476.11

3611 votes

Category
chinese
Evaluated configuration
GPT-5.1
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

GPT-5.1

1,453.32 rating

Confidence interval: 1,446.45 – 1,460.19

8403 votes

Category
coding
Evaluated configuration
GPT-5.1 (High)
Evaluation type
human preference

1,437.47 rating

Confidence interval: 1,430.90 – 1,444.04

9345 votes

Category
coding
Evaluated configuration
GPT-5.1
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

GPT-5.1

1,427.13 rating

Confidence interval: 1,419.11 – 1,435.14

6241 votes

Category
creative_writing
Evaluated configuration
GPT-5.1 (High)
Evaluation type
human preference

1,403.32 rating

Confidence interval: 1,395.52 – 1,411.12

6671 votes

Category
creative_writing
Evaluated configuration
GPT-5.1
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

GPT-5.1

1,450.87 rating

Confidence interval: 1,445.50 – 1,456.24

16710 votes

Category
english
Evaluated configuration
GPT-5.1 (High)
Evaluation type
human preference

1,425.50 rating

Confidence interval: 1,420.34 – 1,430.65

17880 votes

Category
english
Evaluated configuration
GPT-5.1
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

GPT-5.1

1,439.88 rating

Confidence interval: 1,434.78 – 1,444.99

29966 votes

Category
exclude_ties
Evaluated configuration
GPT-5.1 (High)
Evaluation type
human preference

1,411.73 rating

Confidence interval: 1,406.80 – 1,416.65

31657 votes

Category
exclude_ties
Evaluated configuration
GPT-5.1
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

GPT-5.1

1,469.67 rating

Confidence interval: 1,457.92 – 1,481.41

2602 votes

Category
expert
Evaluated configuration
GPT-5.1 (High)
Evaluation type
human preference

1,441.27 rating

Confidence interval: 1,430.47 – 1,452.06

3028 votes

Category
expert
Evaluated configuration
GPT-5.1
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating

GPT-5.1

1,450.39 rating

Confidence interval: 1,430.55 – 1,470.22

944 votes

Category
french
Evaluated configuration
GPT-5.1 (High)
Evaluation type
human preference

1,433.31 rating

Confidence interval: 1,413.05 – 1,453.58

920 votes

Category
french
Evaluated configuration
GPT-5.1
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating

GPT-5.1

1,438.25 rating

Confidence interval: 1,416.44 – 1,460.07

718 votes

Category
german
Evaluated configuration
GPT-5.1 (High)
Evaluation type
human preference

1,416.92 rating

Confidence interval: 1,395.27 – 1,438.57

744 votes

Category
german
Evaluated configuration
GPT-5.1
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

GPT-5.1

1,456.92 rating

Confidence interval: 1,452.12 – 1,461.72

22409 votes

Category
hard_prompts
Evaluated configuration
GPT-5.1 (High)
Evaluation type
human preference

1,434.49 rating

Confidence interval: 1,429.91 – 1,439.07

24333 votes

Category
hard_prompts
Evaluated configuration
GPT-5.1
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

GPT-5.1

1,462.37 rating

Confidence interval: 1,455.51 – 1,469.24

8814 votes

Category
hard_prompts_english
Evaluated configuration
GPT-5.1 (High)
Evaluation type
human preference

1,439.96 rating

Confidence interval: 1,433.42 – 1,446.49

9589 votes

Category
hard_prompts_english
Evaluated configuration
GPT-5.1
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

GPT-5.1

1,430.82 rating

Confidence interval: 1,423.60 – 1,438.03

7742 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
GPT-5.1 (High)
Evaluation type
human preference

1,420.56 rating

Confidence interval: 1,413.62 – 1,427.51

8309 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
GPT-5.1
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

GPT-5.1

1,414.45 rating

Confidence interval: 1,407.11 – 1,421.79

7585 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
GPT-5.1 (High)
Evaluation type
human preference

1,396.94 rating

Confidence interval: 1,389.97 – 1,403.91

8226 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
GPT-5.1
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

GPT-5.1

1,458.59 rating

Confidence interval: 1,447.75 – 1,469.43

3065 votes

Category
industry_legal_and_government
Evaluated configuration
GPT-5.1 (High)
Evaluation type
human preference

1,440.39 rating

Confidence interval: 1,429.98 – 1,450.80

3193 votes

Category
industry_legal_and_government
Evaluated configuration
GPT-5.1
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

GPT-5.1

1,459.35 rating

Confidence interval: 1,451.74 – 1,466.96

6880 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
GPT-5.1 (High)
Evaluation type
human preference

1,439.24 rating

Confidence interval: 1,431.88 – 1,446.60

7241 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
GPT-5.1
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

GPT-5.1

1,448.89 rating

Confidence interval: 1,435.44 – 1,462.34

1867 votes

Category
industry_mathematical
Evaluated configuration
GPT-5.1 (High)
Evaluation type
human preference

1,419.31 rating

Confidence interval: 1,406.88 – 1,431.75

2208 votes

Category
industry_mathematical
Evaluated configuration
GPT-5.1
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

GPT-5.1

1,456.70 rating

Confidence interval: 1,444.96 – 1,468.43

2626 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
GPT-5.1 (High)
Evaluation type
human preference

1,444.55 rating

Confidence interval: 1,433.16 – 1,455.94

2749 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
GPT-5.1
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

GPT-5.1

1,453.86 rating

Confidence interval: 1,448.21 – 1,459.52

14111 votes

Category
industry_software_and_it_services
Evaluated configuration
GPT-5.1 (High)
Evaluation type
human preference

1,436.99 rating

Confidence interval: 1,431.57 – 1,442.42

15354 votes

Category
industry_software_and_it_services
Evaluated configuration
GPT-5.1
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

GPT-5.1

1,427.72 rating

Confidence interval: 1,420.95 – 1,434.49

9359 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
GPT-5.1 (High)
Evaluation type
human preference

1,411.45 rating

Confidence interval: 1,404.97 – 1,417.94

10128 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
GPT-5.1
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

GPT-5.1

1,442.59 rating

Confidence interval: 1,436.32 – 1,448.86

11155 votes

Category
instruction_following
Evaluated configuration
GPT-5.1 (High)
Evaluation type
human preference

1,418.11 rating

Confidence interval: 1,412.18 – 1,424.05

12326 votes

Category
instruction_following
Evaluated configuration
GPT-5.1
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating

GPT-5.1

1,453.38 rating

Confidence interval: 1,425.70 – 1,481.06

459 votes

Category
japanese
Evaluated configuration
GPT-5.1 (High)
Evaluation type
human preference

1,423.34 rating

Confidence interval: 1,395.28 – 1,451.40

460 votes

Category
japanese
Evaluated configuration
GPT-5.1
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating

GPT-5.1

1,399.97 rating

Confidence interval: 1,376.72 – 1,423.22

659 votes

Category
korean
Evaluated configuration
GPT-5.1 (High)
Evaluation type
human preference

1,390.25 rating

Confidence interval: 1,368.21 – 1,412.29

730 votes

Category
korean
Evaluated configuration
GPT-5.1
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

GPT-5.1

1,447.51 rating

Confidence interval: 1,441.20 – 1,453.83

10929 votes

Category
longer_query
Evaluated configuration
GPT-5.1 (High)
Evaluation type
human preference

1,429.65 rating

Confidence interval: 1,423.66 – 1,435.64

12220 votes

Category
longer_query
Evaluated configuration
GPT-5.1
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

GPT-5.1

1,446.09 rating

Confidence interval: 1,434.52 – 1,457.65

2578 votes

Category
math
Evaluated configuration
GPT-5.1 (High)
Evaluation type
human preference

1,409.45 rating

Confidence interval: 1,398.65 – 1,420.25

2962 votes

Category
math
Evaluated configuration
GPT-5.1
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

GPT-5.1

1,449.55 rating

Confidence interval: 1,442.05 – 1,457.04

7245 votes

Category
multi_turn
Evaluated configuration
GPT-5.1 (High)
Evaluation type
human preference

1,432.87 rating

Confidence interval: 1,425.75 – 1,440.00

8253 votes

Category
multi_turn
Evaluated configuration
GPT-5.1
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

GPT-5.1

1,431.25 rating

Confidence interval: 1,426.69 – 1,435.81

24928 votes

Category
non_english
Evaluated configuration
GPT-5.1 (High)
Evaluation type
human preference

1,412.84 rating

Confidence interval: 1,408.41 – 1,417.26

26532 votes

Category
non_english
Evaluated configuration
GPT-5.1
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

GPT-5.1

1,442.71 rating

Confidence interval: 1,439.04 – 1,446.39

41639 votes

Category
overall
Evaluated configuration
GPT-5.1 (High)
Evaluation type
human preference

1,422.18 rating

Confidence interval: 1,418.63 – 1,425.73

44413 votes

Category
overall
Evaluated configuration
GPT-5.1
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating

GPT-5.1

1,440.30 rating

Confidence interval: 1,424.54 – 1,456.06

1321 votes

Category
polish
Evaluated configuration
GPT-5.1
Evaluation type
human preference

1,439.77 rating

Confidence interval: 1,422.89 – 1,456.65

1198 votes

Category
polish
Evaluated configuration
GPT-5.1 (High)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

GPT-5.1

1,435.37 rating

Confidence interval: 1,427.11 – 1,443.63

5210 votes

Category
russian
Evaluated configuration
GPT-5.1 (High)
Evaluation type
human preference

1,425.77 rating

Confidence interval: 1,417.62 – 1,433.93

5396 votes

Category
russian
Evaluated configuration
GPT-5.1
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating

GPT-5.1

1,432.78 rating

Confidence interval: 1,415.51 – 1,450.05

1211 votes

Category
spanish
Evaluated configuration
GPT-5.1 (High)
Evaluation type
human preference

1,418.65 rating

Confidence interval: 1,402.13 – 1,435.17

1303 votes

Category
spanish
Evaluated configuration
GPT-5.1
Evaluation type
human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating

GPT-5.1

1,495.11 rating

Confidence interval: 1,484.81 – 1,505.41

3427 votes

Category
chinese
Evaluated configuration
gpt-5.1-high
Evaluation type
human preference

1,466.22 rating

Confidence interval: 1,456.19 – 1,476.25

3611 votes

Category
chinese
Evaluated configuration
gpt-5.1
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

GPT-5.1

1,453.28 rating

Confidence interval: 1,446.41 – 1,460.15

8411 votes

Category
coding
Evaluated configuration
gpt-5.1-high
Evaluation type
human preference

1,437.59 rating

Confidence interval: 1,431.02 – 1,444.16

9360 votes

Category
coding
Evaluated configuration
gpt-5.1
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

GPT-5.1

1,427.24 rating

Confidence interval: 1,419.23 – 1,435.26

6246 votes

Category
creative_writing
Evaluated configuration
gpt-5.1-high
Evaluation type
human preference

1,403.61 rating

Confidence interval: 1,395.81 – 1,411.42

6669 votes

Category
creative_writing
Evaluated configuration
gpt-5.1
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

GPT-5.1

1,450.89 rating

Confidence interval: 1,445.52 – 1,456.26

16710 votes

Category
english
Evaluated configuration
gpt-5.1-high
Evaluation type
human preference

1,425.53 rating

Confidence interval: 1,420.38 – 1,430.69

17887 votes

Category
english
Evaluated configuration
gpt-5.1
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

GPT-5.1

1,439.95 rating

Confidence interval: 1,434.85 – 1,445.06

29974 votes

Category
exclude_ties
Evaluated configuration
gpt-5.1-high
Evaluation type
human preference

1,411.89 rating

Confidence interval: 1,406.97 – 1,416.82

31680 votes

Category
exclude_ties
Evaluated configuration
gpt-5.1
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

GPT-5.1

1,469.89 rating

Confidence interval: 1,458.14 – 1,481.64

2604 votes

Category
expert
Evaluated configuration
gpt-5.1-high
Evaluation type
human preference

1,441.18 rating

Confidence interval: 1,430.38 – 1,451.97

3029 votes

Category
expert
Evaluated configuration
gpt-5.1
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating

GPT-5.1

1,449.98 rating

Confidence interval: 1,430.11 – 1,469.84

944 votes

Category
french
Evaluated configuration
gpt-5.1-high
Evaluation type
human preference

1,432.60 rating

Confidence interval: 1,412.32 – 1,452.88

921 votes

Category
french
Evaluated configuration
gpt-5.1
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating

GPT-5.1

1,438.14 rating

Confidence interval: 1,416.29 – 1,459.98

718 votes

Category
german
Evaluated configuration
gpt-5.1-high
Evaluation type
human preference

1,416.82 rating

Confidence interval: 1,395.14 – 1,438.50

744 votes

Category
german
Evaluated configuration
gpt-5.1
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

GPT-5.1

1,456.94 rating

Confidence interval: 1,452.14 – 1,461.75

22414 votes

Category
hard_prompts
Evaluated configuration
gpt-5.1-high
Evaluation type
human preference

1,434.59 rating

Confidence interval: 1,430.01 – 1,439.17

24348 votes

Category
hard_prompts
Evaluated configuration
gpt-5.1
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

GPT-5.1

1,462.37 rating

Confidence interval: 1,455.50 – 1,469.24

8812 votes

Category
hard_prompts_english
Evaluated configuration
gpt-5.1-high
Evaluation type
human preference

1,439.96 rating

Confidence interval: 1,433.42 – 1,446.49

9592 votes

Category
hard_prompts_english
Evaluated configuration
gpt-5.1
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

GPT-5.1

1,431.14 rating

Confidence interval: 1,423.92 – 1,438.35

7739 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
gpt-5.1-high
Evaluation type
human preference

1,420.76 rating

Confidence interval: 1,413.82 – 1,427.71

8312 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
gpt-5.1
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

GPT-5.1

1,414.50 rating

Confidence interval: 1,407.15 – 1,421.84

7585 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
gpt-5.1-high
Evaluation type
human preference

1,396.97 rating

Confidence interval: 1,390.00 – 1,403.95

8232 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
gpt-5.1
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

GPT-5.1

1,458.72 rating

Confidence interval: 1,447.88 – 1,469.57

3065 votes

Category
industry_legal_and_government
Evaluated configuration
gpt-5.1-high
Evaluation type
human preference

1,440.39 rating

Confidence interval: 1,429.97 – 1,450.80

3190 votes

Category
industry_legal_and_government
Evaluated configuration
gpt-5.1
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

GPT-5.1

1,459.43 rating

Confidence interval: 1,451.82 – 1,467.04

6883 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
gpt-5.1-high
Evaluation type
human preference

1,439.54 rating

Confidence interval: 1,432.18 – 1,446.90

7242 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
gpt-5.1
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

GPT-5.1

1,449.06 rating

Confidence interval: 1,435.61 – 1,462.52

1868 votes

Category
industry_mathematical
Evaluated configuration
gpt-5.1-high
Evaluation type
human preference

1,419.16 rating

Confidence interval: 1,406.72 – 1,431.60

2211 votes

Category
industry_mathematical
Evaluated configuration
gpt-5.1
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

GPT-5.1

1,456.81 rating

Confidence interval: 1,445.08 – 1,468.55

2628 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
gpt-5.1-high
Evaluation type
human preference

1,444.59 rating

Confidence interval: 1,433.19 – 1,455.98

2750 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
gpt-5.1
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

GPT-5.1

1,453.89 rating

Confidence interval: 1,448.23 – 1,459.55

14122 votes

Category
industry_software_and_it_services
Evaluated configuration
gpt-5.1-high
Evaluation type
human preference

1,437.06 rating

Confidence interval: 1,431.63 – 1,442.48

15374 votes

Category
industry_software_and_it_services
Evaluated configuration
gpt-5.1
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

GPT-5.1

1,427.85 rating

Confidence interval: 1,421.08 – 1,434.62

9361 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
gpt-5.1-high
Evaluation type
human preference

1,411.69 rating

Confidence interval: 1,405.19 – 1,418.18

10125 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
gpt-5.1
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

GPT-5.1

1,442.56 rating

Confidence interval: 1,436.29 – 1,448.84

11162 votes

Category
instruction_following
Evaluated configuration
gpt-5.1-high
Evaluation type
human preference

1,418.12 rating

Confidence interval: 1,412.18 – 1,424.06

12334 votes

Category
instruction_following
Evaluated configuration
gpt-5.1
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating

GPT-5.1

1,453.21 rating

Confidence interval: 1,425.50 – 1,480.92

459 votes

Category
japanese
Evaluated configuration
gpt-5.1-high
Evaluation type
human preference

1,423.19 rating

Confidence interval: 1,395.10 – 1,451.27

460 votes

Category
japanese
Evaluated configuration
gpt-5.1
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating

GPT-5.1

1,400.48 rating

Confidence interval: 1,377.29 – 1,423.68

663 votes

Category
korean
Evaluated configuration
gpt-5.1-high
Evaluation type
human preference

1,391.90 rating

Confidence interval: 1,369.85 – 1,413.94

731 votes

Category
korean
Evaluated configuration
gpt-5.1
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

GPT-5.1

1,447.72 rating

Confidence interval: 1,441.41 – 1,454.04

10937 votes

Category
longer_query
Evaluated configuration
gpt-5.1-high
Evaluation type
human preference

1,429.87 rating

Confidence interval: 1,423.88 – 1,435.87

12231 votes

Category
longer_query
Evaluated configuration
gpt-5.1
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

GPT-5.1

1,446.18 rating

Confidence interval: 1,434.61 – 1,457.75

2579 votes

Category
math
Evaluated configuration
gpt-5.1-high
Evaluation type
human preference

1,409.43 rating

Confidence interval: 1,398.63 – 1,420.23

2965 votes

Category
math
Evaluated configuration
gpt-5.1
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

GPT-5.1

1,449.52 rating

Confidence interval: 1,442.03 – 1,457.02

7244 votes

Category
multi_turn
Evaluated configuration
gpt-5.1-high
Evaluation type
human preference

1,433.01 rating

Confidence interval: 1,425.87 – 1,440.14

8247 votes

Category
multi_turn
Evaluated configuration
gpt-5.1
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

GPT-5.1

1,431.33 rating

Confidence interval: 1,426.76 – 1,435.89

24940 votes

Category
non_english
Evaluated configuration
gpt-5.1-high
Evaluation type
human preference

1,413.05 rating

Confidence interval: 1,408.62 – 1,417.47

26546 votes

Category
non_english
Evaluated configuration
gpt-5.1
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

GPT-5.1

1,442.74 rating

Confidence interval: 1,439.06 – 1,446.41

41651 votes

Category
overall
Evaluated configuration
gpt-5.1-high
Evaluation type
human preference

1,422.28 rating

Confidence interval: 1,418.72 – 1,425.83

44434 votes

Category
overall
Evaluated configuration
gpt-5.1
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating

GPT-5.1

1,440.26 rating

Confidence interval: 1,424.50 – 1,456.03

1321 votes

Category
polish
Evaluated configuration
gpt-5.1
Evaluation type
human preference

1,439.73 rating

Confidence interval: 1,422.84 – 1,456.61

1198 votes

Category
polish
Evaluated configuration
gpt-5.1-high
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

GPT-5.1

1,435.32 rating

Confidence interval: 1,427.05 – 1,443.58

5211 votes

Category
russian
Evaluated configuration
gpt-5.1-high
Evaluation type
human preference

1,426.10 rating

Confidence interval: 1,417.95 – 1,434.26

5402 votes

Category
russian
Evaluated configuration
gpt-5.1
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating

GPT-5.1

1,432.63 rating

Confidence interval: 1,415.34 – 1,449.92

1211 votes

Category
spanish
Evaluated configuration
gpt-5.1-high
Evaluation type
human preference

1,418.52 rating

Confidence interval: 1,401.95 – 1,435.08

1301 votes

Category
spanish
Evaluated configuration
gpt-5.1
Evaluation type
human preference

Run it locally

Inference · memory estimate

GPT-5.1

Closed weights. No supported local deployment or GPU requirement is published.

API cost

USD / month

Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.

GPT-5.1

Capabilities

Context window
400,000 tokens
Maximum input
272,000 tokens*
Maximum output
128,000 tokens
Reasoning
Yes
Tool calling
Yes
Structured output
Yes*
Open weights
No
Knowledge cutoff
2024-09-30
API mode
Chat*
Image input
Yes*
PDF input
Yes*
Parallel tool calls
Yes*
Prompt caching
Yes*
System messages
Yes*
Tool choice
Yes*
Web search
Yes*
Model license
Proprietary

Input modalities

  • text
  • image

Output modalities

  • text
  • image*

System configuration

Detailed specifications

Specifications · 37 fields
cache read input token cost
1.25e-7*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
cache read input token cost batches
6.25e-8*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
cache read input token cost flex
6.25e-8*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
cache read input token cost priority
2.5e-7*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
default reasoning effort
none*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
deprecation date
2027-04-01*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
input cost per token
1.25e-6*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
input cost per token batches
6.25e-7*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
input cost per token flex
6.25e-7*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
input cost per token priority
2.5e-6*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
litellm provider
openai*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
max input tokens
272,000*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
max output tokens
128,000*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
max tokens
128,000*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
mode
chat*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
output cost per token
1.0e-5*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
output cost per token batches
5.0e-6*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
output cost per token flex
5.0e-6*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
output cost per token priority
2.0e-5*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
search context cost per query
search_context_size_high
0.01*
search_context_size_low
0.01*
search_context_size_medium
0.01*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supported endpoints
  • /v1/chat/completions*
  • /v1/responses*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supported modalities
  • text*
  • image*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supported output modalities
  • text*
  • image*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports function calling
Yes*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports minimal reasoning effort
No*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports native streaming
Yes*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports none reasoning effort
Yes*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports parallel function calling
Yes*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports pdf input
Yes*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports prompt caching
Yes*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports reasoning
Yes*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports response schema
Yes*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports system messages
Yes*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports tool choice
Yes*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports vision
Yes*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports web search
Yes*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports xhigh reasoning effort
No*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*

* Provisional data