geekradar
Int
Explore GeekRadar

More to explore

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

GPT-5.5

AI model Released

API mode
Chat*
Context window
1,050,000 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-5.5 159.4* GPT-5.5 · 95% interval 156.9–162.8

Human preference · Arena

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

GPT-5.5 1466.8 GPT-5.5 · 95% interval 1463.1–1470.4 · 70,949 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-5.5

Radar task score

Unrated

3/4 core tests · not enough evidence

5 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

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

GPT-5.5 Not available

Novel problem solving

Mystery Game Puzzles · 25%

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

GPT-5.5 56.0*% Approx. 95% interval: 46.2–65.8%

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

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

GPT-5.5 85.3*% Approx. 95% interval: 81.1–89.4%

Factual answers

SimpleQA Verified · 25%

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

GPT-5.5 63.0*% Approx. 95% interval: 60.0–66.0%

Research mathematics

FrontierMath Tier 4 v2 · Separate result

The hardest private FrontierMath problems, corrected v2 set, with Python tools. Separate from Tiers 1-3 in the core score.

GPT-5.5 72.5*% Approx. 95% interval: 58.5–86.5%

Visual spatial reasoning

Furniture Assembly · Separate result

Assembly-error detection from photos and manuals, with zoom and Python tools. Uses model-assisted grading; not a general vision score.

GPT-5.5 44.2*% Approx. 95% interval: 31.6–56.7%

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.

Benchmark results

  • Reported score · version unreported · intelligence54.80*Platform unreported Compare results

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-5.5

1,534.07 rating

Confidence interval: 1,524.38 – 1,543.77

4448 votes

Category
chinese
Evaluated configuration
GPT-5.5
Evaluation type
human preference

1,525.21 rating

Confidence interval: 1,515.66 – 1,534.75

4490 votes

Category
chinese
Evaluated configuration
GPT-5.5 (High)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

GPT-5.5

1,494.42 rating

Confidence interval: 1,488.78 – 1,500.07

19166 votes

Category
coding
Evaluated configuration
GPT-5.5 (High)
Evaluation type
human preference

1,482.95 rating

Confidence interval: 1,477.41 – 1,488.50

20064 votes

Category
coding
Evaluated configuration
GPT-5.5
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

GPT-5.5

1,455.10 rating

Confidence interval: 1,448.61 – 1,461.59

13129 votes

Category
creative_writing
Evaluated configuration
GPT-5.5 (High)
Evaluation type
human preference

1,452.45 rating

Confidence interval: 1,445.94 – 1,458.95

13377 votes

Category
creative_writing
Evaluated configuration
GPT-5.5
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

GPT-5.5

1,470.36 rating

Confidence interval: 1,465.60 – 1,475.11

31558 votes

Category
english
Evaluated configuration
GPT-5.5 (High)
Evaluation type
human preference

1,468.46 rating

Confidence interval: 1,463.73 – 1,473.20

32237 votes

Category
english
Evaluated configuration
GPT-5.5
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

GPT-5.5

1,476.70 rating

Confidence interval: 1,471.97 – 1,481.43

52734 votes

Category
exclude_ties
Evaluated configuration
GPT-5.5 (High)
Evaluation type
human preference

1,470.62 rating

Confidence interval: 1,465.90 – 1,475.34

54151 votes

Category
exclude_ties
Evaluated configuration
GPT-5.5
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

GPT-5.5

1,507.29 rating

Confidence interval: 1,499.59 – 1,514.99

7403 votes

Category
expert
Evaluated configuration
GPT-5.5 (High)
Evaluation type
human preference

1,503.34 rating

Confidence interval: 1,495.69 – 1,510.99

7686 votes

Category
expert
Evaluated configuration
GPT-5.5
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating

GPT-5.5

1,485.01 rating

Confidence interval: 1,471.34 – 1,498.68

2504 votes

Category
french
Evaluated configuration
GPT-5.5
Evaluation type
human preference

1,482.34 rating

Confidence interval: 1,468.71 – 1,495.98

2507 votes

Category
french
Evaluated configuration
GPT-5.5 (High)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating

GPT-5.5

1,480.86 rating

Confidence interval: 1,461.92 – 1,499.79

1113 votes

Category
german
Evaluated configuration
GPT-5.5
Evaluation type
human preference

1,459.31 rating

Confidence interval: 1,440.39 – 1,478.24

1053 votes

Category
german
Evaluated configuration
GPT-5.5 (High)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

GPT-5.5

1,488.91 rating

Confidence interval: 1,484.57 – 1,493.24

45556 votes

Category
hard_prompts
Evaluated configuration
GPT-5.5 (High)
Evaluation type
human preference

1,485.79 rating

Confidence interval: 1,481.49 – 1,490.09

47256 votes

Category
hard_prompts
Evaluated configuration
GPT-5.5
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

GPT-5.5

1,483.27 rating

Confidence interval: 1,477.84 – 1,488.70

21954 votes

Category
hard_prompts_english
Evaluated configuration
GPT-5.5
Evaluation type
human preference

1,482.60 rating

Confidence interval: 1,477.14 – 1,488.06

21208 votes

Category
hard_prompts_english
Evaluated configuration
GPT-5.5 (High)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

GPT-5.5

1,478.23 rating

Confidence interval: 1,471.99 – 1,484.47

13727 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
GPT-5.5 (High)
Evaluation type
human preference

1,472.99 rating

Confidence interval: 1,466.78 – 1,479.20

14099 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
GPT-5.5
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

GPT-5.5

1,448.68 rating

Confidence interval: 1,442.67 – 1,454.68

16712 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
GPT-5.5 (High)
Evaluation type
human preference

1,447.71 rating

Confidence interval: 1,441.75 – 1,453.67

17187 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
GPT-5.5
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

GPT-5.5

1,491.43 rating

Confidence interval: 1,482.74 – 1,500.11

5622 votes

Category
industry_legal_and_government
Evaluated configuration
GPT-5.5 (High)
Evaluation type
human preference

1,481.60 rating

Confidence interval: 1,473.16 – 1,490.04

5918 votes

Category
industry_legal_and_government
Evaluated configuration
GPT-5.5
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

GPT-5.5

1,485.45 rating

Confidence interval: 1,478.97 – 1,491.93

11623 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
GPT-5.5 (High)
Evaluation type
human preference

1,484.60 rating

Confidence interval: 1,478.15 – 1,491.05

11788 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
GPT-5.5
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

GPT-5.5

1,495.99 rating

Confidence interval: 1,485.90 – 1,506.08

3979 votes

Category
industry_mathematical
Evaluated configuration
GPT-5.5 (High)
Evaluation type
human preference

1,490.06 rating

Confidence interval: 1,480.01 – 1,500.10

4074 votes

Category
industry_mathematical
Evaluated configuration
GPT-5.5
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

GPT-5.5

1,465.11 rating

Confidence interval: 1,456.14 – 1,474.08

5319 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
GPT-5.5
Evaluation type
human preference

1,456.67 rating

Confidence interval: 1,447.78 – 1,465.57

5242 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
GPT-5.5 (High)
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

GPT-5.5

1,492.92 rating

Confidence interval: 1,487.95 – 1,497.90

27468 votes

Category
industry_software_and_it_services
Evaluated configuration
GPT-5.5 (High)
Evaluation type
human preference

1,486.51 rating

Confidence interval: 1,481.57 – 1,491.45

28332 votes

Category
industry_software_and_it_services
Evaluated configuration
GPT-5.5
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

GPT-5.5

1,466.20 rating

Confidence interval: 1,460.43 – 1,471.98

18138 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
GPT-5.5 (High)
Evaluation type
human preference

1,463.89 rating

Confidence interval: 1,458.13 – 1,469.66

18501 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
GPT-5.5
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

GPT-5.5

1,478.56 rating

Confidence interval: 1,473.30 – 1,483.82

24014 votes

Category
instruction_following
Evaluated configuration
GPT-5.5 (High)
Evaluation type
human preference

1,475.13 rating

Confidence interval: 1,469.93 – 1,480.34

24792 votes

Category
instruction_following
Evaluated configuration
GPT-5.5
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating

GPT-5.5

1,498.93 rating

Confidence interval: 1,477.68 – 1,520.18

910 votes

Category
japanese
Evaluated configuration
GPT-5.5 (High)
Evaluation type
human preference

1,475.77 rating

Confidence interval: 1,453.00 – 1,498.53

810 votes

Category
japanese
Evaluated configuration
GPT-5.5
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating

GPT-5.5

1,459.99 rating

Confidence interval: 1,441.74 – 1,478.24

1184 votes

Category
korean
Evaluated configuration
GPT-5.5 (High)
Evaluation type
human preference

1,446.25 rating

Confidence interval: 1,427.71 – 1,464.78

1190 votes

Category
korean
Evaluated configuration
GPT-5.5
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

GPT-5.5

1,484.19 rating

Confidence interval: 1,479.21 – 1,489.18

32024 votes

Category
longer_query
Evaluated configuration
GPT-5.5 (High)
Evaluation type
human preference

1,482.33 rating

Confidence interval: 1,477.40 – 1,487.25

33382 votes

Category
longer_query
Evaluated configuration
GPT-5.5
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

GPT-5.5

1,486.88 rating

Confidence interval: 1,476.43 – 1,497.32

3509 votes

Category
math
Evaluated configuration
GPT-5.5
Evaluation type
human preference

1,478.43 rating

Confidence interval: 1,468.09 – 1,488.78

3474 votes

Category
math
Evaluated configuration
GPT-5.5 (High)
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

GPT-5.5

1,475.92 rating

Confidence interval: 1,469.25 – 1,482.59

11829 votes

Category
multi_turn
Evaluated configuration
GPT-5.5 (High)
Evaluation type
human preference

1,472.35 rating

Confidence interval: 1,465.80 – 1,478.90

12373 votes

Category
multi_turn
Evaluated configuration
GPT-5.5
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

GPT-5.5

1,467.19 rating

Confidence interval: 1,462.70 – 1,471.68

37818 votes

Category
non_english
Evaluated configuration
GPT-5.5 (High)
Evaluation type
human preference

1,459.65 rating

Confidence interval: 1,455.22 – 1,464.09

38711 votes

Category
non_english
Evaluated configuration
GPT-5.5
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

GPT-5.5

1,471.57 rating

Confidence interval: 1,467.88 – 1,475.26

69377 votes

Category
overall
Evaluated configuration
GPT-5.5 (High)
Evaluation type
human preference

1,466.75 rating

Confidence interval: 1,463.10 – 1,470.40

70949 votes

Category
overall
Evaluated configuration
GPT-5.5
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating

GPT-5.5

1,465.83 rating

Confidence interval: 1,448.37 – 1,483.29

1170 votes

Category
polish
Evaluated configuration
GPT-5.5 (High)
Evaluation type
human preference

1,459.57 rating

Confidence interval: 1,442.28 – 1,476.86

1195 votes

Category
polish
Evaluated configuration
GPT-5.5
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

GPT-5.5

1,473.08 rating

Confidence interval: 1,465.45 – 1,480.71

7401 votes

Category
russian
Evaluated configuration
GPT-5.5
Evaluation type
human preference

1,472.66 rating

Confidence interval: 1,465.02 – 1,480.29

7340 votes

Category
russian
Evaluated configuration
GPT-5.5 (High)
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating

GPT-5.5

1,468.82 rating

Confidence interval: 1,454.52 – 1,483.12

1943 votes

Category
spanish
Evaluated configuration
GPT-5.5 (High)
Evaluation type
human preference

1,457.24 rating

Confidence interval: 1,443.17 – 1,471.31

2029 votes

Category
spanish
Evaluated configuration
GPT-5.5
Evaluation type
human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating

GPT-5.5

1,533.22 rating

Confidence interval: 1,523.53 – 1,542.92

4460 votes

Category
chinese
Evaluated configuration
gpt-5.5
Evaluation type
human preference

1,525.12 rating

Confidence interval: 1,515.58 – 1,534.67

4503 votes

Category
chinese
Evaluated configuration
gpt-5.5-high
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

GPT-5.5

1,494.30 rating

Confidence interval: 1,488.65 – 1,499.94

19167 votes

Category
coding
Evaluated configuration
gpt-5.5-high
Evaluation type
human preference

1,483.26 rating

Confidence interval: 1,477.70 – 1,488.81

20064 votes

Category
coding
Evaluated configuration
gpt-5.5
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

GPT-5.5

1,454.96 rating

Confidence interval: 1,448.46 – 1,461.45

13156 votes

Category
creative_writing
Evaluated configuration
gpt-5.5-high
Evaluation type
human preference

1,452.17 rating

Confidence interval: 1,445.66 – 1,458.68

13402 votes

Category
creative_writing
Evaluated configuration
gpt-5.5
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

GPT-5.5

1,470.34 rating

Confidence interval: 1,465.58 – 1,475.09

31558 votes

Category
english
Evaluated configuration
gpt-5.5-high
Evaluation type
human preference

1,469.13 rating

Confidence interval: 1,464.39 – 1,473.87

32235 votes

Category
english
Evaluated configuration
gpt-5.5
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

GPT-5.5

1,476.40 rating

Confidence interval: 1,471.66 – 1,481.13

52755 votes

Category
exclude_ties
Evaluated configuration
gpt-5.5-high
Evaluation type
human preference

1,470.65 rating

Confidence interval: 1,465.93 – 1,475.37

54194 votes

Category
exclude_ties
Evaluated configuration
gpt-5.5
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

GPT-5.5

1,507.76 rating

Confidence interval: 1,500.05 – 1,515.48

7408 votes

Category
expert
Evaluated configuration
gpt-5.5-high
Evaluation type
human preference

1,503.52 rating

Confidence interval: 1,495.86 – 1,511.18

7681 votes

Category
expert
Evaluated configuration
gpt-5.5
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating

GPT-5.5

1,484.72 rating

Confidence interval: 1,471.02 – 1,498.43

2512 votes

Category
french
Evaluated configuration
gpt-5.5
Evaluation type
human preference

1,483.03 rating

Confidence interval: 1,469.36 – 1,496.70

2519 votes

Category
french
Evaluated configuration
gpt-5.5-high
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating

GPT-5.5

1,480.36 rating

Confidence interval: 1,461.39 – 1,499.34

1113 votes

Category
german
Evaluated configuration
gpt-5.5
Evaluation type
human preference

1,459.20 rating

Confidence interval: 1,440.22 – 1,478.19

1054 votes

Category
german
Evaluated configuration
gpt-5.5-high
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

GPT-5.5

1,488.76 rating

Confidence interval: 1,484.42 – 1,493.10

45575 votes

Category
hard_prompts
Evaluated configuration
gpt-5.5-high
Evaluation type
human preference

1,485.98 rating

Confidence interval: 1,481.68 – 1,490.29

47284 votes

Category
hard_prompts
Evaluated configuration
gpt-5.5
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

GPT-5.5

1,483.80 rating

Confidence interval: 1,478.37 – 1,489.24

21960 votes

Category
hard_prompts_english
Evaluated configuration
gpt-5.5
Evaluation type
human preference

1,482.74 rating

Confidence interval: 1,477.28 – 1,488.20

21233 votes

Category
hard_prompts_english
Evaluated configuration
gpt-5.5-high
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

GPT-5.5

1,478.13 rating

Confidence interval: 1,471.88 – 1,484.38

13723 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
gpt-5.5-high
Evaluation type
human preference

1,473.08 rating

Confidence interval: 1,466.86 – 1,479.29

14103 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
gpt-5.5
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

GPT-5.5

1,448.75 rating

Confidence interval: 1,442.74 – 1,454.77

16720 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
gpt-5.5-high
Evaluation type
human preference

1,447.46 rating

Confidence interval: 1,441.50 – 1,453.43

17195 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
gpt-5.5
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

GPT-5.5

1,490.74 rating

Confidence interval: 1,482.04 – 1,499.44

5618 votes

Category
industry_legal_and_government
Evaluated configuration
gpt-5.5-high
Evaluation type
human preference

1,481.38 rating

Confidence interval: 1,472.93 – 1,489.82

5928 votes

Category
industry_legal_and_government
Evaluated configuration
gpt-5.5
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

GPT-5.5

1,485.49 rating

Confidence interval: 1,479.00 – 1,491.98

11612 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
gpt-5.5-high
Evaluation type
human preference

1,484.70 rating

Confidence interval: 1,478.24 – 1,491.16

11789 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
gpt-5.5
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

GPT-5.5

1,496.14 rating

Confidence interval: 1,486.04 – 1,506.24

3983 votes

Category
industry_mathematical
Evaluated configuration
gpt-5.5-high
Evaluation type
human preference

1,489.55 rating

Confidence interval: 1,479.48 – 1,499.62

4067 votes

Category
industry_mathematical
Evaluated configuration
gpt-5.5
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

GPT-5.5

1,464.98 rating

Confidence interval: 1,455.99 – 1,473.96

5328 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
gpt-5.5
Evaluation type
human preference

1,456.67 rating

Confidence interval: 1,447.76 – 1,465.59

5239 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
gpt-5.5-high
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

GPT-5.5

1,492.74 rating

Confidence interval: 1,487.76 – 1,497.72

27462 votes

Category
industry_software_and_it_services
Evaluated configuration
gpt-5.5-high
Evaluation type
human preference

1,486.83 rating

Confidence interval: 1,481.88 – 1,491.77

28330 votes

Category
industry_software_and_it_services
Evaluated configuration
gpt-5.5
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

GPT-5.5

1,466.08 rating

Confidence interval: 1,460.30 – 1,471.86

18181 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
gpt-5.5-high
Evaluation type
human preference

1,463.48 rating

Confidence interval: 1,457.71 – 1,469.26

18531 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
gpt-5.5
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

GPT-5.5

1,478.47 rating

Confidence interval: 1,473.20 – 1,483.74

24032 votes

Category
instruction_following
Evaluated configuration
gpt-5.5-high
Evaluation type
human preference

1,475.13 rating

Confidence interval: 1,469.92 – 1,480.34

24814 votes

Category
instruction_following
Evaluated configuration
gpt-5.5
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating

GPT-5.5

1,498.50 rating

Confidence interval: 1,477.10 – 1,519.89

907 votes

Category
japanese
Evaluated configuration
gpt-5.5-high
Evaluation type
human preference

1,475.69 rating

Confidence interval: 1,452.70 – 1,498.67

806 votes

Category
japanese
Evaluated configuration
gpt-5.5
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating

GPT-5.5

1,459.28 rating

Confidence interval: 1,441.01 – 1,477.56

1189 votes

Category
korean
Evaluated configuration
gpt-5.5-high
Evaluation type
human preference

1,444.86 rating

Confidence interval: 1,426.27 – 1,463.45

1184 votes

Category
korean
Evaluated configuration
gpt-5.5
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

GPT-5.5

1,484.28 rating

Confidence interval: 1,479.28 – 1,489.27

32045 votes

Category
longer_query
Evaluated configuration
gpt-5.5-high
Evaluation type
human preference

1,482.27 rating

Confidence interval: 1,477.34 – 1,487.20

33399 votes

Category
longer_query
Evaluated configuration
gpt-5.5
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

GPT-5.5

1,487.06 rating

Confidence interval: 1,476.60 – 1,497.51

3511 votes

Category
math
Evaluated configuration
gpt-5.5
Evaluation type
human preference

1,478.75 rating

Confidence interval: 1,468.41 – 1,489.09

3478 votes

Category
math
Evaluated configuration
gpt-5.5-high
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

GPT-5.5

1,475.85 rating

Confidence interval: 1,469.17 – 1,482.53

11832 votes

Category
multi_turn
Evaluated configuration
gpt-5.5-high
Evaluation type
human preference

1,472.59 rating

Confidence interval: 1,466.04 – 1,479.15

12373 votes

Category
multi_turn
Evaluated configuration
gpt-5.5
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

GPT-5.5

1,466.89 rating

Confidence interval: 1,462.40 – 1,471.39

37842 votes

Category
non_english
Evaluated configuration
gpt-5.5-high
Evaluation type
human preference

1,459.25 rating

Confidence interval: 1,454.81 – 1,463.70

38749 votes

Category
non_english
Evaluated configuration
gpt-5.5
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

GPT-5.5

1,471.34 rating

Confidence interval: 1,467.65 – 1,475.03

69401 votes

Category
overall
Evaluated configuration
gpt-5.5-high
Evaluation type
human preference

1,466.80 rating

Confidence interval: 1,463.15 – 1,470.46

70985 votes

Category
overall
Evaluated configuration
gpt-5.5
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating

GPT-5.5

1,464.41 rating

Confidence interval: 1,446.93 – 1,481.90

1171 votes

Category
polish
Evaluated configuration
gpt-5.5-high
Evaluation type
human preference

1,459.18 rating

Confidence interval: 1,441.88 – 1,476.47

1197 votes

Category
polish
Evaluated configuration
gpt-5.5
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

GPT-5.5

1,472.89 rating

Confidence interval: 1,465.26 – 1,480.53

7412 votes

Category
russian
Evaluated configuration
gpt-5.5
Evaluation type
human preference

1,472.46 rating

Confidence interval: 1,464.82 – 1,480.10

7354 votes

Category
russian
Evaluated configuration
gpt-5.5-high
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating

GPT-5.5

1,468.08 rating

Confidence interval: 1,453.75 – 1,482.41

1945 votes

Category
spanish
Evaluated configuration
gpt-5.5-high
Evaluation type
human preference

1,457.01 rating

Confidence interval: 1,442.92 – 1,471.10

2038 votes

Category
spanish
Evaluated configuration
gpt-5.5
Evaluation type
human preference

Run it locally

Inference · memory estimate

GPT-5.5

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-5.5

Capabilities

Context window
1,050,000 tokens
Maximum input
1,050,000 tokens*
Maximum output
128,000 tokens
Reasoning
Yes
Tool calling
Yes
Structured output
Yes*
Open weights
No
Knowledge cutoff
2025-12-01
API mode
Chat*
Declared context window
1.05M*
Model type
LLM (reasoning)*
Declared modalities
Text, Vision → Text*
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
  • pdf

Output modalities

  • text

System configuration

Detailed specifications

Specifications 1 · 13 fields
api providers
OpenAI, Azure*
Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
OpenAI*
price_unit
Not reported*
price_tiers
Not reported*
context window
1.05M*
Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
OpenAI*
price_unit
Not reported*
price_tiers
Not reported*
developer
OpenAI*
Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
OpenAI*
price_unit
Not reported*
price_tiers
Not reported*
input price
5*
Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
OpenAI*
price_unit
Not reported*
price_tiers
Not reported*
intelligence
54.8*
Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
OpenAI*
price_unit
Not reported*
price_tiers
Not reported*
license
Proprietary*
Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
OpenAI*
price_unit
Not reported*
price_tiers
Not reported*
max output
128K*
Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
OpenAI*
price_unit
Not reported*
price_tiers
Not reported*
modality
Text, Vision → Text*
Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
OpenAI*
price_unit
Not reported*
price_tiers
Not reported*
model type
LLM (reasoning)*
Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
OpenAI*
price_unit
Not reported*
price_tiers
Not reported*
name
GPT-5.5*
Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
OpenAI*
price_unit
Not reported*
price_tiers
Not reported*
open weights
no*
Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
OpenAI*
price_unit
Not reported*
price_tiers
Not reported*
output price
30*
Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
OpenAI*
price_unit
Not reported*
price_tiers
Not reported*
release date
2026*
Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
OpenAI*
price_unit
Not reported*
price_tiers
Not reported*
Specifications 2 · 47 fields
cache read input token cost
5.0e-7*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.5*
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 above 272k tokens
1.0e-6*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.5*
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 above 272k tokens batches
5.0e-7*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.5*
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 above 272k tokens flex
5.0e-7*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.5*
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
2.5e-7*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.5*
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
2.5e-7*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.5*
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
1.25e-6*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.5*
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
5.0e-6*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.5*
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 above 272k tokens
1.0e-5*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.5*
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 above 272k tokens batches
5.0e-6*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.5*
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 above 272k tokens flex
5.0e-6*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.5*
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
2.5e-6*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.5*
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
2.5e-6*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.5*
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
1.25e-5*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.5*
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-5.5*
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
1,050,000*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.5*
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-5.5*
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-5.5*
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-5.5*
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
3.0e-5*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.5*
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 above 272k tokens
4.5e-5*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.5*
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 above 272k tokens batches
2.25e-5*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.5*
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 above 272k tokens flex
2.25e-5*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.5*
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
1.5e-5*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.5*
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
1.5e-5*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.5*
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
7.5e-5*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.5*
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.*
regional processing uplift multiplier eu
1.1*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.5*
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.*
regional processing uplift multiplier us
1.1*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.5*
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-5.5*
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/batch*
  • /v1/responses*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.5*
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-5.5*
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*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.5*
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-5.5*
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-5.5*
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-5.5*
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-5.5*
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-5.5*
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-5.5*
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-5.5*
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-5.5*
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-5.5*
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-5.5*
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-5.5*
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 search
Yes*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.5*
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-5.5*
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-5.5*
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
Yes*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-5.5*
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