GPT-5.2

OpenAILegacy

Input price: $1.75; Per 1 million tokens (USD)
Output price: $14.00; Per 1 million tokens (USD)
Effort levels: 5total; Default: None
Benchmark results: 8total; Benchmark types: 4

Model information

API model ID: gpt-5.2
release date: Unknown
effort: None (default) / Low / Med / High / Xhigh
Effort source: Based on "Reasoning.effort supports: none (default), low, medium, high and xhigh." on the OpenAI model page (developers.openai.com/api/docs/models/gpt-5.2, retrieved 2026-11-13).
Claude Code: unknown
Codex: unknown
Availability notes: Not collected (the official model list for Claude Code and the one for Codex were not checked this time).

Price (USD per 1 million tokens)

Prices do not vary by effort; token consumption does.

input	$1.75
output	$14.00
cache read	$0.18
cache write	—

Standard unit price.

Input $1.75 Cached input $0.175 Output $14.00

Source: https://developers.openai.com/api/docs/models/gpt-5.2

Benchmark results

Benchmark	effort	Score	Source cost (metric)	measured/reported by	source	Conditions and extraction method
τ²-bench airline (v1.0.1)None (default)	None	52.5%	$0.054Average cost in USD to run one trajectory in this domain	Sierra	τ²-bench leaderboard submission gpt-5-2-none_sierra_2026-02-26 (sierra-research/tau2-bench, MIT)third-party · Retrieved 2026-11-13	τ²-bench leaderboard submission gpt-5-2-none_sierra_2026-02-26 (submission_type standard, tau2_bench_version 1.0.1). Submitter "Sierra", model_organization "OpenAI": Run by Sierra, which operates τ²-bench (third-party measurement). Verified on the leaderboard (trajectories available, prompts not modified, no questions omitted). The value is pass^1 (%). reasoning_effort "none". User simulator gpt-5.2 (reasoning_effort low). Submission-level evaluation_date 2026-05-26. Notes summary: 4 trial runs; seed 300.transcribed from table Source excerpt airline.pass_1=52.5; airline.cost=0.053692803500000004Location In submissions/gpt-5-2-none_sierra_2026-02-26/submission.json: results.airline.pass_1 (line 22 of file), results.airline.cost (line 26). model_name "GPT-5.2". methodology.notes (line 56)
τ²-bench airline (v1.0.1)High	High	83.0%	$0.11Average cost in USD to run one trajectory in this domain	Sierra	τ²-bench leaderboard submission gpt-5-2_sierra_2026-02-26 (sierra-research/tau2-bench, MIT)third-party · Retrieved 2026-11-13	τ²-bench leaderboard submission gpt-5-2_sierra_2026-02-26 (submission_type standard, tau2_bench_version 1.0.1). Submitter "Sierra", model_organization "OpenAI": Run by Sierra, which operates τ²-bench (third-party measurement). Verified on the leaderboard (trajectories available, prompts not modified, no questions omitted). The value is pass^1 (%). reasoning_effort "high". User simulator gpt-5.2. 4 trial runs (based on "_gpt-5.2_4trials" in the trajectories filename). The notes and evaluation_date (2026-05-05) refer to banking_knowledge (AllTools) ("Banking_knowledge domain only"); the evaluation date, seed, and simulator effort for this domain are not stated.transcribed from table Source excerpt airline.pass_1=83.0; airline.cost=0.11379Location In submissions/gpt-5-2_sierra_2026-02-26/submission.json: results.airline.pass_1 (line 22 of file), results.airline.cost (line 26). model_name "GPT-5.2". trajectory_files.airline (line 14), methodology.user_simulator (line 55). methodology.notes (line 56) and evaluation_date (line 53) refer to banking_knowledge (AllTools)
τ²-bench banking_knowledge (v1.0.1)None (default)	None	12.6%	$0.24Average cost in USD to run one trajectory in this domain	Sierra	τ²-bench leaderboard submission gpt-5-2-none_sierra_2026-02-26 (sierra-research/tau2-bench, MIT)third-party · Retrieved 2026-11-13	τ²-bench leaderboard submission gpt-5-2-none_sierra_2026-02-26 (submission_type standard, tau2_bench_version 1.0.1). Submitter "Sierra", model_organization "OpenAI": Run by Sierra, which operates τ²-bench (third-party measurement). Verified on the leaderboard (trajectories available, prompts not modified, no questions omitted). The value is pass^1 (%). reasoning_effort "none". User simulator gpt-5.2 (reasoning_effort low). Search configuration retrieval_config "qwen_embeddings". Evaluation date 2026-05-26. Notes summary: rescored on 2026-07-15 following a scoring correction in v1.0.1; 4 trial runs; seed 300.transcribed from table Source excerpt banking_knowledge.pass_1=12.63; banking_knowledge.cost=0.2433424974226804Location In submissions/gpt-5-2-none_sierra_2026-02-26/submission.json: results.banking_knowledge.pass_1 (line 43 of file), results.banking_knowledge.cost (line 47). model_name "GPT-5.2". methodology.notes (line 56)
τ²-bench banking_knowledge (v1.0.1)High	High	32.2%	—	Sierra	τ²-bench leaderboard submission gpt-5-2_sierra_2026-02-26 (sierra-research/tau2-bench, MIT)third-party · Retrieved 2026-11-13	τ²-bench leaderboard submission gpt-5-2_sierra_2026-02-26 (submission_type standard, tau2_bench_version 1.0.1). Submitter "Sierra", model_organization "OpenAI": Run by Sierra, which operates τ²-bench (third-party measurement). Verified on the leaderboard (trajectories available, prompts not modified, no questions omitted). The value is pass^1 (%). reasoning_effort "high". User simulator gpt-5.2 (reasoning_effort low). Search configuration retrieval_config "alltools". Evaluation date 2026-05-05. Notes summary: rescored on 2026-07-15 following a scoring correction in v1.0.1; 4 trial runs; seed 300.transcribed from table Source excerpt banking_knowledge.pass_1=32.22Location In submissions/gpt-5-2_sierra_2026-02-26/submission.json: results.banking_knowledge.pass_1 (line 43 of file). model_name "GPT-5.2". methodology.notes (line 56)
τ²-bench retail (v1.0.1)None (default)	None	75.0%	$0.048Average cost in USD to run one trajectory in this domain	Sierra	τ²-bench leaderboard submission gpt-5-2-none_sierra_2026-02-26 (sierra-research/tau2-bench, MIT)third-party · Retrieved 2026-11-13	τ²-bench leaderboard submission gpt-5-2-none_sierra_2026-02-26 (submission_type standard, tau2_bench_version 1.0.1). Submitter "Sierra", model_organization "OpenAI": Run by Sierra, which operates τ²-bench (third-party measurement). Verified on the leaderboard (trajectories available, prompts not modified, no questions omitted). The value is pass^1 (%). reasoning_effort "none". User simulator gpt-5.2 (reasoning_effort low). Submission-level evaluation_date 2026-05-26. Notes summary: 4 trial runs; seed 300.transcribed from table Source excerpt retail.pass_1=75.0; retail.cost=0.048219267434210525Location In submissions/gpt-5-2-none_sierra_2026-02-26/submission.json: results.retail.pass_1 (line 29 of file), results.retail.cost (line 33). model_name "GPT-5.2". methodology.notes (line 56)
τ²-bench retail (v1.0.1)High	High	81.6%	$0.072Average cost in USD to run one trajectory in this domain	Sierra	τ²-bench leaderboard submission gpt-5-2_sierra_2026-02-26 (sierra-research/tau2-bench, MIT)third-party · Retrieved 2026-11-13	τ²-bench leaderboard submission gpt-5-2_sierra_2026-02-26 (submission_type standard, tau2_bench_version 1.0.1). Submitter "Sierra", model_organization "OpenAI": Run by Sierra, which operates τ²-bench (third-party measurement). Verified on the leaderboard (trajectories available, prompts not modified, no questions omitted). The value is pass^1 (%). reasoning_effort "high". User simulator gpt-5.2. 4 trial runs (based on "_gpt-5.2_4trials" in the trajectories filename). The notes and evaluation_date (2026-05-05) refer to banking_knowledge (AllTools) ("Banking_knowledge domain only"); the evaluation date, seed, and simulator effort for this domain are not stated.transcribed from table Source excerpt retail.pass_1=81.58; retail.cost=0.07156Location In submissions/gpt-5-2_sierra_2026-02-26/submission.json: results.retail.pass_1 (line 29 of file), results.retail.cost (line 33). model_name "GPT-5.2". trajectory_files.retail (line 15), methodology.user_simulator (line 55). methodology.notes (line 56) and evaluation_date (line 53) refer to banking_knowledge (AllTools)
τ²-bench telecom (v1.0.1)None (default)	None	57.2%	$0.049Average cost in USD to run one trajectory in this domain	Sierra	τ²-bench leaderboard submission gpt-5-2-none_sierra_2026-02-26 (sierra-research/tau2-bench, MIT)third-party · Retrieved 2026-11-13	τ²-bench leaderboard submission gpt-5-2-none_sierra_2026-02-26 (submission_type standard, tau2_bench_version 1.0.1). Submitter "Sierra", model_organization "OpenAI": Run by Sierra, which operates τ²-bench (third-party measurement). Verified on the leaderboard (trajectories available, prompts not modified, no questions omitted). The value is pass^1 (%). reasoning_effort "none". User simulator gpt-5.2 (reasoning_effort low). Submission-level evaluation_date 2026-05-26. Notes summary: 4 trial runs; seed 300.transcribed from table Source excerpt telecom.pass_1=57.23684210526315; telecom.cost=0.04937742280701755Location In submissions/gpt-5-2-none_sierra_2026-02-26/submission.json: results.telecom.pass_1 (line 36 of file), results.telecom.cost (line 40). model_name "GPT-5.2". methodology.notes (line 56)
τ²-bench telecom (v1.0.1)High	High	89.7%	$0.093Average cost in USD to run one trajectory in this domain	Sierra	τ²-bench leaderboard submission gpt-5-2_sierra_2026-02-26 (sierra-research/tau2-bench, MIT)third-party · Retrieved 2026-11-13	τ²-bench leaderboard submission gpt-5-2_sierra_2026-02-26 (submission_type standard, tau2_bench_version 1.0.1). Submitter "Sierra", model_organization "OpenAI": Run by Sierra, which operates τ²-bench (third-party measurement). Verified on the leaderboard (trajectories available, prompts not modified, no questions omitted). The value is pass^1 (%). reasoning_effort "high". User simulator gpt-5.2. 4 trial runs (based on "_gpt-5.2_4trials" in the trajectories filename). The notes and evaluation_date (2026-05-05) refer to banking_knowledge (AllTools) ("Banking_knowledge domain only"); the evaluation date, seed, and simulator effort for this domain are not stated.transcribed from table Source excerpt telecom.pass_1=89.69; telecom.cost=0.09312Location In submissions/gpt-5-2_sierra_2026-02-26/submission.json: results.telecom.pass_1 (line 36 of file), results.telecom.cost (line 40). model_name "GPT-5.2". trajectory_files.telecom (line 16), methodology.user_simulator (line 55). methodology.notes (line 56) and evaluation_date (line 53) refer to banking_knowledge (AllTools)

Related rankings

References

https://developers.openai.com/api/docs/models/gpt-5.2