Skip to content

OpenAI · Chat

GPT 5.2

OpenAI 🇺🇸ChatGPT familyOne of its sources says the weights aren't publicly available.The maker currently lists 8 Jun 2027 as the deprecation date. Plans can change.

Newer version: GPT 6. Our catalogue has no release date for GPT 6. We compared the version names in our catalogue.

From Netmind's listing:
GPT-5.2 is an advanced reasoning model from OpenAI, balancing strong step-by-step problem solving with broad general capability. It supports multimodal input, tool and function calling, and prompt caching, and is designed for demanding coding, analysis, and agentic applications.
llminfo IQ
133.4
Max context
410K
Listings
76

Evidence and sources

llminfo IQ 133.4, ranked among chat models. From 440 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 111.5, 95% interval 105–118. From 19 benchmark families across 13 sources. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedGood value (56.6). Cheaper per task than its benchmark results predict. From 63 benchmarks with measured task costs. Plenty of data behind it.How Value for money worksYap score: tokens used per coding task vs. models with the same resultsTypical (49 ±14). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.Median 21,051 output tokens per task at default effort.How the Yap score worksReleased 11 Dec 2025Maker HQ: US (according to OpenAI's own website)
All rankings: #140 on OpenRouter this month #178 on OpenRouter this week #191 on OpenRouter today #403 on NanoGPT recentlySources: OpenAI API data, Models.dev data, LMArena data, LiteLLM data, AI/ML API data, NetMind.AI, llminfo researchPrimary data from OpenAI API from Models.dev: name, weights availability from LMArena: variant from LiteLLM: deprecation date from AI/ML API: primary mode from NetMind.AI: description from llminfo research: release date

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Trade-offs

No open weights

The weights aren't public, so you can't run it yourself.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.

Input & output

as stated by the model's providers
Text
Images
Files
Text
Images

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt cachingPDF inputWeb searchBatch API

Listings

 OpenAIgpt-5.2Sources: GenAI Prices data, LiteLLM data, Models.dev data, OpenAI API data272K$1.75cache read $0.175batch $0.875$14.00batch $7.00——
 Qihang AIgpt-5.2Source: Models.dev data400K$0.25$2.00——
 Microsoft Azuregpt-5.2-batch · batchSource: Helicone Costs dataNot published by the provider$0.875$7.00——
 OpenRouterInference by OpenAIopenai/gpt-5.2 · flexSource: OpenRouter data docs272K$0.875cache read $0.0875$7.00141.5838ms
 Vercelopenai/gpt-5.2-batch · batchSource: Vercel AI Gateway data400K$0.875cache read $0.0875$7.00——
 Unoroutergpt-5.2Source: Models.dev data400K$1.05$8.40——
 Meganovaopenai/gpt-5.2Source: MegaNova data400K$1.40$11.20——
 Poeopenai/gpt-5.2Source: Models.dev data400K$1.5909cache read $0.1591$12.727——
 Jiekougpt-5.2Source: Models.dev data400K$1.6625cache read $0.1662$13.30——
 Tokenmixgpt-5.2Sources: TokenMix data, TokenMix PricingNot published by the provider$1.6975$13.58——

10 listings without a price are hidden.

Included in plans

Copilot EnterprisegithubSubscription$39/moextra use billed past the allowancePlan page
Copilot ProgithubSubscription$10/moextra use billed past the allowancePlan page
Copilot Pro+githubSubscription$39/moextra use billed past the allowancePlan page
Copilot BusinessgithubSubscription$19/moextra use billed past the allowancePlan page
Copilot MaxgithubSubscription$100/moextra use billed past the allowancePlan page

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Human preference

Arena ELO68 related benchmarks · 134 results
Source: LMArena data · Nov 2026
Arena ELO
Chinese
Creative Writing
Document
Document Style-Controlled
English
Show 122 more resultsHide 122 results
Exclude Ties
Expert
French
German
Hard Prompts
Hard Prompts English
Industry Mathematical
Industry Medicine and Healthcare
Industry Software and It Services
Japanese
Korean
Longer Query
Multi Turn
Non English
Polish
Russian
Search Factuality
Search Style-Controlled
Spanish
Style-Controlled
Text Factuality
Text Factuality - Chinese
Text Factuality - Creative Writing
Text Factuality - English
Text Factuality - Exclude Ties
Text Factuality - Expert
Text Factuality - French
Text Factuality - German
Text Factuality - Hard Prompts
Text Factuality - Hard Prompts English
Text Factuality - Industry Mathematical
Text Factuality - Korean
Text Factuality - Longer Query
Text Factuality - Multi Turn
Text Factuality - Non English
Text Factuality - Polish
Text Factuality - Russian
Text Factuality - Spanish
Vision
Vision - Captioning
Vision - Chinese
Vision - Creative Writing Vision
Vision - Diagram
Vision - English
Vision - Entity Recognition
Vision - Homework
Vision - Humor
Vision Style-Controlled

Agentic

BrowseComp3 related benchmarks · 7 results
BrowseComp
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Long Context · xhigh
OpenAI GPT-5.4 launch table
standard tool-use setup · xhigh
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Long Context 128k
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Long Context 256k
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Design Arena EloSource: Design Arena Leaderboards data · Nov 2026
FinanceAgent v1.1OpenAI GPT-5.4 launch table · Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
GAIA4 results
Source: GAIA Leaderboard data · Dec 2025
Difficulty level
Difficulty not reported
MCP Atlas4 results
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI GPT-5.4 launch table
Scale MCP-Atlas · xhigh
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Open Agent Leaderboard6 related benchmarks · 30 results
SWE-bench
Source: Open Agent Leaderboard results data docs
By agent · task: swebench · route: openai/azure
AppWorld test_normal
Source: Open Agent Leaderboard results data docs
By agent · task: appworld_test_normal · subset: test_normal · route: openai/azure
BrowseCompPlus
Source: Open Agent Leaderboard results data docs
By agent · task: browsecompplus · route: openai/azure
Tau Bench 2 airline
Source: Open Agent Leaderboard results data docs
By agent · task: tau2_airline · subset: airline · route: openai/azure
Tau Bench 2 retail
Source: Open Agent Leaderboard results data docs
By agent · task: tau2_retail · subset: retail · route: openai/azure
Tau Bench 2 telecom
Source: Open Agent Leaderboard results data docs
By agent · task: tau2_telecom · subset: telecom · route: openai/azure
OpenHandsSource: OpenHands Index data
OSWorld-VerifiedOpenAI GPT-5.4 launch table · Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
SWE-Bench Pro2 results
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reasoning effort · Public
Effort not reported
Tau2 Retail14 related benchmarks · 26 results
Tau2 Retail
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Tau2 Telecom
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
tau2-bench v1 airline pass^1
Source: Sierra tau-bench Leaderboard data docs · May 2026
submission-gpt-5-2_sierra_2026-02-26, usersim-gpt-5.2, effort-high
submission-gpt-5-2-none_sierra_2026-02-26, usersim-gpt-5.2, effort-none
tau2-bench v1 airline pass^2
Source: Sierra tau-bench Leaderboard data docs · May 2026
submission-gpt-5-2_sierra_2026-02-26, usersim-gpt-5.2, effort-high
submission-gpt-5-2-none_sierra_2026-02-26, usersim-gpt-5.2, effort-none
tau2-bench v1 airline pass^3
Source: Sierra tau-bench Leaderboard data docs · May 2026
submission-gpt-5-2_sierra_2026-02-26, usersim-gpt-5.2, effort-high
submission-gpt-5-2-none_sierra_2026-02-26, usersim-gpt-5.2, effort-none
tau2-bench v1 airline pass^4
Source: Sierra tau-bench Leaderboard data docs · May 2026
submission-gpt-5-2_sierra_2026-02-26, usersim-gpt-5.2, effort-high
submission-gpt-5-2-none_sierra_2026-02-26, usersim-gpt-5.2, effort-none
Show 16 more resultsHide 16 results
tau2-bench v1 retail pass^1
Source: Sierra tau-bench Leaderboard data docs · May 2026
submission-gpt-5-2_sierra_2026-02-26, usersim-gpt-5.2, effort-high
submission-gpt-5-2-none_sierra_2026-02-26, usersim-gpt-5.2, effort-none
tau2-bench v1 retail pass^2
Source: Sierra tau-bench Leaderboard data docs · May 2026
submission-gpt-5-2_sierra_2026-02-26, usersim-gpt-5.2, effort-high
submission-gpt-5-2-none_sierra_2026-02-26, usersim-gpt-5.2, effort-none
tau2-bench v1 retail pass^3
Source: Sierra tau-bench Leaderboard data docs · May 2026
submission-gpt-5-2_sierra_2026-02-26, usersim-gpt-5.2, effort-high
submission-gpt-5-2-none_sierra_2026-02-26, usersim-gpt-5.2, effort-none
tau2-bench v1 retail pass^4
Source: Sierra tau-bench Leaderboard data docs · May 2026
submission-gpt-5-2_sierra_2026-02-26, usersim-gpt-5.2, effort-high
submission-gpt-5-2-none_sierra_2026-02-26, usersim-gpt-5.2, effort-none
tau2-bench v1 telecom pass^1
Source: Sierra tau-bench Leaderboard data docs · May 2026
submission-gpt-5-2_sierra_2026-02-26, usersim-gpt-5.2, effort-high
submission-gpt-5-2-none_sierra_2026-02-26, usersim-gpt-5.2, effort-none
tau2-bench v1 telecom pass^2
Source: Sierra tau-bench Leaderboard data docs · May 2026
submission-gpt-5-2_sierra_2026-02-26, usersim-gpt-5.2, effort-high
submission-gpt-5-2-none_sierra_2026-02-26, usersim-gpt-5.2, effort-none
tau2-bench v1 telecom pass^3
Source: Sierra tau-bench Leaderboard data docs · May 2026
submission-gpt-5-2_sierra_2026-02-26, usersim-gpt-5.2, effort-high
submission-gpt-5-2-none_sierra_2026-02-26, usersim-gpt-5.2, effort-none
tau2-bench v1 telecom pass^4
Source: Sierra tau-bench Leaderboard data docs · May 2026
submission-gpt-5-2_sierra_2026-02-26, usersim-gpt-5.2, effort-high
submission-gpt-5-2-none_sierra_2026-02-26, usersim-gpt-5.2, effort-none
tau3-bench v1 banking-knowledge4 related benchmarks · 8 results
pass^1
Source: Sierra tau-bench Leaderboard data docs · May 2026
submission-gpt-5-2_sierra_2026-02-26, usersim-gpt-5.2, effort-high, retrieval-alltools
submission-gpt-5-2-none_sierra_2026-02-26, usersim-gpt-5.2, effort-none, retrieval-qwen-embeddings
pass^2
Source: Sierra tau-bench Leaderboard data docs · May 2026
submission-gpt-5-2_sierra_2026-02-26, usersim-gpt-5.2, effort-high, retrieval-alltools
submission-gpt-5-2-none_sierra_2026-02-26, usersim-gpt-5.2, effort-none, retrieval-qwen-embeddings
pass^3
Source: Sierra tau-bench Leaderboard data docs · May 2026
submission-gpt-5-2_sierra_2026-02-26, usersim-gpt-5.2, effort-high, retrieval-alltools
submission-gpt-5-2-none_sierra_2026-02-26, usersim-gpt-5.2, effort-none, retrieval-qwen-embeddings
pass^4
Source: Sierra tau-bench Leaderboard data docs · May 2026
submission-gpt-5-2_sierra_2026-02-26, usersim-gpt-5.2, effort-high, retrieval-alltools
submission-gpt-5-2-none_sierra_2026-02-26, usersim-gpt-5.2, effort-none, retrieval-qwen-embeddings
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI GPT-5.4 launch table
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted
WebArena-VerifiedDOM + screenshot interaction · Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.

Reasoning

ARC-AGI4 related benchmarks · 17 results
ARC-AGI
Source: Epoch AI Benchmarking Hub data
Reasoning effort
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
ARC-AGI 2
Source: Epoch AI Benchmarking Hub data
Reasoning effort
Effort not reported
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted · Verified
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reasoning effort · Verified
Effort not reported
ARC-AGI-1
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reasoning effort · Verified
Effort not reported
v2
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
CL-bench5 related benchmarks · 20 results
Overall
Reported by Tencent Hunyuan / Fudan NLP Group · via BenchBoard docs
By site model-mode label · benchmark-owner leaderboard run · 1899 tasks · GPT-5.1 judge · low reasoning effort · candidate API snapshot and exact candidate harness not specified on public leaderboard
Source: Epoch AI Benchmarking Hub data
Reasoning effort
Effort not reported
Domain Knowledge Reasoning
Reported by Tencent Hunyuan / Fudan NLP Group · via BenchBoard docs
By site model-mode label · benchmark-owner leaderboard run · 1899 tasks · GPT-5.1 judge · low reasoning effort · candidate API snapshot and exact candidate harness not specified on public leaderboard
Source: Epoch AI Benchmarking Hub data
Reasoning effort
Effort not reported
Empirical Discovery & Simulation
Reported by Tencent Hunyuan / Fudan NLP Group · via BenchBoard docs
By site model-mode label · benchmark-owner leaderboard run · 1899 tasks · GPT-5.1 judge · low reasoning effort · candidate API snapshot and exact candidate harness not specified on public leaderboard
Source: Epoch AI Benchmarking Hub data
Reasoning effort
Effort not reported
Procedural Task Execution
Reported by Tencent Hunyuan / Fudan NLP Group · via BenchBoard docs
By site model-mode label · benchmark-owner leaderboard run · 1899 tasks · GPT-5.1 judge · low reasoning effort · candidate API snapshot and exact candidate harness not specified on public leaderboard
Source: Epoch AI Benchmarking Hub data
Reasoning effort
Effort not reported
Rule System Application
Reported by Tencent Hunyuan / Fudan NLP Group · via BenchBoard docs
By site model-mode label · benchmark-owner leaderboard run · 1899 tasks · GPT-5.1 judge · low reasoning effort · candidate API snapshot and exact candidate harness not specified on public leaderboard
Source: Epoch AI Benchmarking Hub data
Reasoning effort
Effort not reported
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reasoning effort · no tools
Effort not reported
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
OfficeQAOpenAI GPT-5.4 launch table · Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI GPT-5.4 launch table

Coding

SWE-bench Verified5 related benchmarks · 7 results
SWE-bench Verified
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
SWE-Lancer (IC-Diamond subset)
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
ValsSource: Vals AI

Math

AIME 20252 results
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
FrontierMath5 related benchmarks · 15 results
FrontierMath
Source: Epoch AI Benchmarking Hub data
Reasoning effort
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Tier 1-3 (v2)
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI GPT-5.4 launch table
Tier 4
Source: Epoch AI Benchmarking Hub data
Reasoning effort
Tier 4 (v2)
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI GPT-5.4 launch table
HMMT 2025Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
HMMT Feb 25Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.

Vision

CharXiv Reasoningreasoning · xhigh · Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
CharXiv-RSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
MMMU-Pro7 results
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
xhigh
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
VideoMMMU2 results
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

OCR

General

Multilingual

EKI EstonianSource: Keelemudelite mõõdupuu data docs
MMMLU3 results
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Science

GPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
GPQA Diamond8 results
Source: Epoch AI Benchmarking Hub data
Reasoning effort
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI GPT-5.4 launch table
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted

Long context

Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
xhigh
Show 1 more resultHide 1 result

Factuality

Instruction following

Safety

PhareSource: Phare

Knowledge

Other

Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
HealthBench4 related benchmarks · 6 results
HealthBench
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
GPT-5.2 Thinking · system-card implementation · raw score
Consensus
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
GPT-5.2 Thinking · system-card implementation · raw score
Hard
Source: HealthBench Hard (Arcophos) data docs · Feb 2026
Raw/unadjusted HealthBench Hard score as evaluated by Baichuan in its M3 report, distinct from OpenAI’s length-adjusted protocol.
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
GPT-5.2 Thinking · system-card implementation · raw score
Source: HealthBench Hard (Arcophos) data docs · Reported by the model's developer. The source relaying it did not verify it. · Jun 2026
length-adjusted, max reasoning effort, GPT-5.6 system card Table 6 column GPT-5.2 (38.9 unadjusted, 2585 chars)
Professional
Source: Clinical Benchmarks data docs · Reported by the model's developer. The source relaying it did not verify it. claim · Jun 2026
Horangi36 related benchmarks · 36 results
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
internal spreadsheet tasks · ChatGPT heavy
OpenAI internal benchmark
Nejumi 428 related benchmarks · 28 results
ALT_バイアス
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.2-2025-12-11: xhigh-effort
ALT_倫理・道徳
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.2-2025-12-11: xhigh-effort
ALT_制御性
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.2-2025-12-11: xhigh-effort
ALT_堅牢性
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.2-2025-12-11: xhigh-effort
ALT_毒性
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.2-2025-12-11: xhigh-effort
ALT_真実性
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.2-2025-12-11: xhigh-effort
Show 22 more resultsHide 22 results
AVG_jaster_0shot
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.2-2025-12-11: xhigh-effort
AVG_jaster_2shots
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.2-2025-12-11: xhigh-effort
GLP_アプリケーション開発
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.2-2025-12-11: xhigh-effort
GLP_コーディング
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.2-2025-12-11: xhigh-effort
GLP_一般的知識
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.2-2025-12-11: xhigh-effort
GLP_基礎的言語性能
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.2-2025-12-11: xhigh-effort
GLP_専門的知識
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.2-2025-12-11: xhigh-effort
GLP_応用的言語性能
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.2-2025-12-11: xhigh-effort
GLP_情報検索
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.2-2025-12-11: xhigh-effort
GLP_意味解析
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.2-2025-12-11: xhigh-effort
GLP_抽象的推論
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.2-2025-12-11: xhigh-effort
GLP_推論能力
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.2-2025-12-11: xhigh-effort
GLP_数学的推論
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.2-2025-12-11: xhigh-effort
GLP_構文解析
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.2-2025-12-11: xhigh-effort
GLP_知識・質問応答
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.2-2025-12-11: xhigh-effort
GLP_翻訳
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.2-2025-12-11: xhigh-effort
GLP_表現
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.2-2025-12-11: xhigh-effort
GLP_論理的推論
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.2-2025-12-11: xhigh-effort
GLP_関数呼び出し
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.2-2025-12-11: xhigh-effort
TOTAL_SCORE
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.2-2025-12-11: xhigh-effort
アラインメント(ALT)_AVG
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.2-2025-12-11: xhigh-effort
汎用的言語性能(GLP)_AVG
Source: Nejumi Leaderboard 4 data docs
openai/gpt-5.2-2025-12-11: xhigh-effort
SurveyReview v1.012 related benchmarks · 12 results
Structure · MAE
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Comprehensiveness · MAE
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Comprehensiveness · MSE
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Criticalness · MAE
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Criticalness · MSE
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Four dimensions · Average MAE
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Show 6 more resultsHide 6 results
Four dimensions · Average MSE
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Overall · Human-aligned Score
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Overall · Reason Quality Score
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Readability · MAE
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Readability · MSE
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Structure · MSE
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
SWE-Lancer IC Diamondxhigh · 40/237 infrastructure failures omitted · Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Data by LLM Stats · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · LMArena, CC BY 4.0 (licence) · BullshitBench by Peter Gostev, MIT (licence) · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · Keelemudelite mõõdupuu: Independent LLM leaderboard for Estonian. Eesti Keele Instituut. https://moodupuu.eki.ee, CC BY 4.0. Latest per-benchmark results selected with partial-run flags retained. (licence) · HalluHard: Fan, Delsad, Flammarion and Andriushchenko (EPFL), arXiv:2602.01031 · Arcophos. HealthBench Hard Leaderboard. https://healthbenchhard.ai. CC BY 4.0. Source document linked on each result. (licence) · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence) · Horangi 4, Weights & Biases Korea; public publisher-selected numeric evaluation results · JMLE2026-Bench and IgakuQA119 by Naoto Iwase; results licence not stated (code MIT, question data CC BY 4.0). · LLM Chess by Maxim Saplin, Apache-2.0 (Copyright [2024] [Maxim Saplin]) (licence) · MineBench, MIT (licence) · Multi-SWE-bench experiments (multi-swe-bench/experiments), Apache-2.0; resolved-rate fractions converted to percentages (licence) · Nejumi Leaderboard 4, Weights & Biases Japan; public publisher-selected numeric evaluation results · OmniDocBench (OpenDataLab), Apache-2.0 (licence) · Open Agent Leaderboard results (Exgentic), CDLA-Permissive-2.0; agreement text at https://cdla.dev/permissive-2-0/. Fractions shown as percentages. (licence) · OpenHands Index (All Hands AI), Apache-2.0 (licence) · Phare (Giskard), CC BY 4.0 (licence) · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence) · SpreadsheetBench (Renmin University of China and contributors), spreadsheetbench.github.io. · SWE-fficiency (swefficiency.com) leaderboard materials, CC BY 4.0; Human Expert reference row omitted (licence) · Steel.dev Agent Leaderboards, MIT (licence) · Sierra Research tau2-bench leaderboard submissions (github.com/sierra-research/tau2-bench), MIT (licence) · UzLiB, Tahrirchi (Abror Shopulatov). Public LEADERBOARD.md numbers; repository MIT covers software and documentation, no separate results licence stated and none asserted. · Vectara Hallucination Leaderboard, Apache-2.0 (licence) · WeirdML v3 by Håvard Tveit Ihle (Norwegian Defence Research Establishment). API costs supported by Epoch AI, METR and NDRE.

Also known as: azure/eu/gpt-5.2, azure/gpt-5.2, azure/gpt-5.2-2025-12-11, azure/gpt-5.2@eastus2, azure/us/gpt-5.2, chatgpt/gpt-5.2, databricks-gpt-5-2, databricks/databricks-gpt-5-2, gmi/openai/gpt-5.2, gpt-5-2, gpt-5.2-2025-12-11, gpt-5.2-high, gpt-5.2-low, gpt-5.2-search, gpt-5.2-search-non-reasoning, gpt-52, openai-gpt-5.2, openai-gpt-52, openai/gpt-5-2, openai/gpt-5.2, openai/gpt-5.2-2025-12-11, openai/gpt-5.2-batch, openai/gpt-5.2-fast, openai/gpt-5.2:batch, perplexity/openai/gpt-5.2, replicate/openai/gpt-5.2

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works