OpenAI: GPT-5.5
GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It featur…
openai/gpt-5.5-20260423
GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling large-scale reasoning, coding, and multimodal workflows within a single system.
Specifications & capabilities
- Input
- file, image, text
- Output
- text
- Context window · tokens
- 1050000
- Knowledge cutoff
- 2025-12-01
- Published model ID
- gpt-5.5-2026-04-23
- Capabilities
- fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch
Description source ↗Evaluations
1–20 / 227
1,475.506
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality German
- dimension
- factuality
- metric
- Arena rating
- rank
- 2
- sample size
- 607
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-5.5
- confidence lower
- 1455.3781566892444
- confidence upper
- 1495.6339378805897
Original result ↗1,508.44
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Japanese
- dimension
- factuality
- metric
- Arena rating
- rank
- 3
- sample size
- 583
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-5.5 (High)
- confidence lower
- 1488.0941739746481
- confidence upper
- 1528.7852387615976
Original result ↗92.845%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Amazon Bedrock
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 3
- sample size
- 396
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 2
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- record_kind
- aggregate
- provider_name
- Amazon Bedrock
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-01T19:13:06.559Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- GPQA Diamond · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 396
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.928451
- accuracy_std_dev
- 0.0025249999999999995
- cost_per_task_usd
- 0.3476244823232323
- output_tokens_per_task
- 10405.60101010101
- latency_seconds_per_task
- 112.46052777777778
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 32
- benchmark_evaluation
- true
- openrouter_permaslug
- openai/gpt-5.5-20260423
- source model id
- openai/gpt-5.5-20260423
Original result ↗73.556%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · OpenAI
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 3
- sample size
- 150
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 3
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- tau_bench_verified_airline
- name
- tau2-bench Verified Airline
- record_kind
- aggregate
- provider_name
- OpenAI
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-02T23:08:08.058Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- tau2-bench Verified Airline · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 150
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.7355556666666666
- accuracy_std_dev
- 0.04157400066013479
- cost_per_task_usd
- 0.48569376
- output_tokens_per_task
- 7296.606666666667
- latency_seconds_per_task
- 125.88567333333334
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 27
- benchmark_evaluation
- true
- openrouter_permaslug
- openai/gpt-5.5-20260423
- source model id
- openai/gpt-5.5-20260423
Original result ↗1,478.821
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Polish
- dimension
- factuality
- metric
- Arena rating
- rank
- 4
- sample size
- 713
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-5.5 (High)
- confidence lower
- 1458.0321790708779
- confidence upper
- 1499.6099998276752
Original result ↗1,518.898
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Industry Legal And Government
- dimension
- factuality
- metric
- Arena rating
- rank
- 5
- sample size
- 4615
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-5.5 (High)
- confidence lower
- 1510.1898093524817
- confidence upper
- 1527.6061320023787
Original result ↗1,516.408
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality French
- dimension
- factuality
- metric
- Arena rating
- rank
- 5
- sample size
- 2064
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-5.5 (High)
- confidence lower
- 1504.7094639122256
- confidence upper
- 1528.1069087480137
Original result ↗1,491.611
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Japanese
- dimension
- factuality
- metric
- Arena rating
- rank
- 5
- sample size
- 532
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-5.5
- confidence lower
- 1471.666547164019
- confidence upper
- 1511.5553097639468
Original result ↗1,464.332
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality German
- dimension
- factuality
- metric
- Arena rating
- rank
- 5
- sample size
- 558
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-5.5 (High)
- confidence lower
- 1444.6071072567527
- confidence upper
- 1484.0576169561
Original result ↗93.603%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · OpenAI
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 5
- sample size
- 594
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 3
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- record_kind
- aggregate
- provider_name
- OpenAI
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-02T23:25:41.614Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- GPQA Diamond · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 594
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.9360266666666668
- accuracy_std_dev
- 0.0036369299629708854
- cost_per_task_usd
- 0.3141816919191919
- output_tokens_per_task
- 10342.412457912458
- latency_seconds_per_task
- 142.47411952861952
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 26
- benchmark_evaluation
- true
- openrouter_permaslug
- openai/gpt-5.5-20260423
- source model id
- openai/gpt-5.5-20260423
Original result ↗1,455.278
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Korean
- dimension
- factuality
- metric
- Arena rating
- rank
- 6
- sample size
- 604
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-5.5 (High)
- confidence lower
- 1434.901409017926
- confidence upper
- 1475.6550563640405
Original result ↗1,334.709
- source id
- lmarena
- leaderboard name
- LMArena Vision Style Control Homework
- dimension
- multimodal
- metric
- Arena rating
- rank
- 6
- sample size
- 3759
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-5.5 (High)
- confidence lower
- 1324.1946069692142
- confidence upper
- 1345.223233805214
Original result ↗93.687%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Azure
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 6
- sample size
- 1188
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 6
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- record_kind
- aggregate
- provider_name
- Azure
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-01T19:14:07.472Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- GPQA Diamond · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 1188
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.9368683333333334
- accuracy_std_dev
- 0.0040948247690089186
- cost_per_task_usd
- 0.3309691094276094
- output_tokens_per_task
- 10209.419191919193
- latency_seconds_per_task
- 165.12449915824914
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 43
- benchmark_evaluation
- true
- openrouter_permaslug
- openai/gpt-5.5-20260423
- source model id
- openai/gpt-5.5-20260423
Original result ↗1,499.606
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Industry Business And Management And Financial Operations
- dimension
- factuality
- metric
- Arena rating
- rank
- 7
- sample size
- 12132
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-5.5 (High)
- confidence lower
- 1493.9030440462277
- confidence upper
- 1505.3090933126282
Original result ↗1,482.093
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Spanish
- dimension
- factuality
- metric
- Arena rating
- rank
- 7
- sample size
- 1581
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-5.5 (High)
- confidence lower
- 1468.4782774400676
- confidence upper
- 1495.707513218056
Original result ↗1,478.44
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Non English
- dimension
- factuality
- metric
- Arena rating
- rank
- 7
- sample size
- 37229
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-5.5 (High)
- confidence lower
- 1474.8300268565101
- confidence upper
- 1482.0506817385267
Original result ↗93.939%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · auto-routing
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 7
- sample size
- 396
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 2
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- record_kind
- aggregate
- provider_name
- auto-routing
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-01T19:12:11.505Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- GPQA Diamond · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 396
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.939394
- accuracy_std_dev
- 0.0033669999999999534
- cost_per_task_usd
- 0.31252995454545457
- output_tokens_per_task
- 10288.712121212122
- latency_seconds_per_task
- 150.8325505050505
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 132
- benchmark_evaluation
- true
- openrouter_permaslug
- openai/gpt-5.5-20260423
- source model id
- openai/gpt-5.5-20260423
Original result ↗0.095
- source id
- lmarena
- leaderboard name
- LMArena Agent Bash Recovery Steps Overall
- dimension
- agentic
- metric
- Arena score
- rank
- 7
- sample size
- 54039
- evaluated at
- 2026-10-08T00:00:00.000Z
- source model id
- GPT 5.5 (xHigh)
- confidence lower
- 0.08396354616019815
- confidence upper
- 0.10698410517892624
Original result ↗1,531.734
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Expert
- dimension
- factuality
- metric
- Arena rating
- rank
- 8
- sample size
- 6111
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-5.5 (High)
- confidence lower
- 1524.2084074520274
- confidence upper
- 1539.2599683841736
Original result ↗1,484.293
- source id
- lmarena
- leaderboard name
- LMArena Document Overall
- dimension
- productivity
- metric
- Arena rating
- rank
- 8
- sample size
- 27324
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-5.5 (High)
- confidence lower
- 1478.9442834030588
- confidence upper
- 1489.6414381746351
Original result ↗Published prices
61–64 / 64
$49.50
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- us
- model_type
- language
- quote_scope
- gateway_catalog
- billing_scope
- Vercel public catalog; endpoint prices may differ
- context_tokens
- min_inclusive
- 272000
- varies_by_provider
- true
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$33.00
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- us
- model_type
- language
- quote_scope
- gateway_catalog
- billing_scope
- Vercel public catalog; endpoint prices may differ
- context_tokens
- max_exclusive
- 272000
- min_inclusive
- 0
- varies_by_provider
- true
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$82.50
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- us
- model_type
- language
- quote_scope
- gateway_catalog
- service_tier
- fast
- billing_scope
- Vercel public catalog; endpoint prices may differ
- varies_by_provider
- true
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.01
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- request
- Currency
- USD
- Billing conditions
- charge
- web_search
- model_type
- language
- quote_scope
- gateway_catalog
- billing_scope
- Vercel public catalog; endpoint prices may differ
- varies_by_provider
- true
- Billing label
- Web search
- Pricing via
- Vercel AI Gateway
Provider specifications & access
1–4 / 4
- source model id
- gpt-5.5
- hosting
- gateway
- context length
- 1000000
- max output tokens
- 128000
- capabilities
- reasoning
- structuredOutputs
- toolCalling
- visionInput
- webSearch
- source model id
- openai.gpt-5.5
- hosting
- bedrock-managed
- source model id
- openai/gpt-5.5
- hosting
- third-party
- context length
- 1000000
- max output tokens
- 16384
- source model id
- openai/gpt-5.5
- hosting
- vercel-gateway
- context length
- 1000000
- max output tokens
- 128000
- capabilities
- promptCaching
- reasoning
- structuredOutputs
- toolCalling
- visionInput
- webSearch
Safety assessments
1–1 / 1
35 / 100
- source id
- stanfordFMTI
- canonical model id
- openai/gpt-5.5-20260423
- taxonomy
- transparency
- hazard category
- transparency
- hazard name
- Organization transparency
- policy area
- OpenAI
- assessment type
- organization-level disclosure
- metric
- disclosure_score
- result label
- 35 / 100
- sample size
- 100
- updated at
- 2026-11-09T18:08:05.227Z
Source specification observations
1–11 / 11
- field
- context_length
- value
- 1000000
- normalized value
- 1000000
- scope
- source-model
- source id
- cloudflareWorkersAI
- confidence
- 1
- field
- context_length
- value
- 1050000
- normalized value
- 1050000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 1050000
- normalized value
- 1050000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 1000000
- normalized value
- 1000000
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2025-12-01
- normalized value
- 2025-12-01
- precision
- day
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2025-12-01
- normalized value
- 2025-12-01
- precision
- day
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2025-12-01
- normalized value
- 2025-12-01
- precision
- day
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
- field
- max_output_tokens
- value
- 16384
- normalized value
- 16384
- scope
- source-model
- source id
- cloudflareWorkersAI
- confidence
- 1
- field
- max_output_tokens
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
Explore more models