Compare model

openai / Chat

GPT-5.2

openai/gpt-5.2

Complex reasoning & problem solving

Catalog status

Enabled

Research checked

2026-10-06

Price / performance

What it costs to get this result

GDPval wins/ties · Source-reported results, not a composite ranking. Prices use the average of TokenBazaar input and output rates per million tokens; actual spend depends on usage. Test configurations differ.

GPT-5.270.9% · 1 sourced models

Blended price / 1M tokens · log scale

● Current model● Other modelsDashed line: price/score frontier among plotted models
Compare sourced models on this benchmark

Benchmark results

8 reported results

Results are source-attributed, not TokenBazaar measurements. Different tests and thinking variants are not interchangeable.

8 of 8 results

GDPval wins/ties

Knowledge-Work · Vendor-reported

Test conditions and source

OpenAI launch-reported GPT-5.2 Thinking result, not a TokenBazaar default-effort test. Professional tasks use heavy effort; most other evaluations use xhigh; see source footnotes for harness details. Published excerpt: GDPval (wins or ties) Knowledge work tasks 70.9% vs 38.8% (GPT-5)

Tested model: openai/gpt-5.2

OpenAI - Introducing GPT-5.2 · Checked 2026-10-06

70.9%

SWE-Bench Pro (public)

Coding · Vendor-reported

Test conditions and source

OpenAI launch-reported GPT-5.2 Thinking result, not a TokenBazaar default-effort test. Professional tasks use heavy effort; most other evaluations use xhigh; see source footnotes for harness details. Published excerpt: SWE-Bench Pro (public) Software engineering 55.6% vs 50.8%

Tested model: openai/gpt-5.2

OpenAI - Introducing GPT-5.2 · Checked 2026-10-06

55.6%

GPQA Diamond (no tools)

Science · Vendor-reported

Test conditions and source

OpenAI launch-reported GPT-5.2 Thinking result, not a TokenBazaar default-effort test. Professional tasks use heavy effort; most other evaluations use xhigh; see source footnotes for harness details. Published excerpt: GPQA Diamond (no tools) Science questions 92.4% vs 88.1%

Tested model: openai/gpt-5.2

OpenAI - Introducing GPT-5.2 · Checked 2026-10-06

92.4%

CharXiv Reasoning (w/ Python)

Multimodal · Vendor-reported

Test conditions and source

OpenAI launch-reported GPT-5.2 Thinking result, not a TokenBazaar default-effort test. Professional tasks use heavy effort; most other evaluations use xhigh; see source footnotes for harness details. Published excerpt: CharXiv Reasoning (w/ Python) Scientific figure questions 88.7% vs 80.3%

Tested model: openai/gpt-5.2

OpenAI - Introducing GPT-5.2 · Checked 2026-10-06

88.7%

AIME 2025 (no tools)

Math · Vendor-reported

Test conditions and source

OpenAI launch-reported GPT-5.2 Thinking result, not a TokenBazaar default-effort test. Professional tasks use heavy effort; most other evaluations use xhigh; see source footnotes for harness details. Published excerpt: AIME 2025 (no tools) Competition math 100.0% vs 94.0%

Tested model: openai/gpt-5.2

OpenAI - Introducing GPT-5.2 · Checked 2026-10-06

100%

FrontierMath (Tier 1-3)

Math · Vendor-reported

Test conditions and source

OpenAI launch-reported GPT-5.2 Thinking result, not a TokenBazaar default-effort test. Professional tasks use heavy effort; most other evaluations use xhigh; see source footnotes for harness details. Published excerpt: FrontierMath (Tier 1–3) Advanced mathematics 40.3% vs 31.0%

Tested model: openai/gpt-5.2

OpenAI - Introducing GPT-5.2 · Checked 2026-10-06

40.3%

ARC-AGI-1 (Verified)

Reasoning · Vendor-reported

Test conditions and source

OpenAI launch-reported GPT-5.2 Thinking result, not a TokenBazaar default-effort test. Professional tasks use heavy effort; most other evaluations use xhigh; see source footnotes for harness details. Published excerpt: ARC-AGI-1 (Verified) Abstract reasoning 86.2% vs 72.8%

Tested model: openai/gpt-5.2

OpenAI - Introducing GPT-5.2 · Checked 2026-10-06

86.2%

ARC-AGI-2 (Verified)

Reasoning · Vendor-reported

Test conditions and source

OpenAI launch-reported GPT-5.2 Thinking result, not a TokenBazaar default-effort test. Professional tasks use heavy effort; most other evaluations use xhigh; see source footnotes for harness details. Published excerpt: ARC-AGI-2 (Verified) Abstract reasoning 52.9% vs 17.6%

Tested model: openai/gpt-5.2

OpenAI - Introducing GPT-5.2 · Checked 2026-10-06

52.9%

Model specifications

Context window

400K

Published provider limit

Maximum output

128K

Published provider limit

Knowledge cutoff

Aug 31, 2025

Upstream model

Input and output modalities

Provider-reported formats; API compatibility is detailed below.

Input

Not verified

Output

Not verified
Exact model ID
openai/gpt-5.2
Model type
Chat
Context window
400,000 tokens
Maximum output
128,000 tokens
Knowledge cutoff
Aug 31, 2025

A context window is the total conversation budget, not a separate maximum input allowance; generated output and reasoning can use that budget. Published provider limits are not independently tested TokenBazaar request limits.

Versions and thinking levels

Choose from 4 enabled versions. The exact ID determines the version and its price; benchmark scores do not carry over between variants.

GPT-5.2Selected₹84.00 in / ₹672.00 out per 1M tokens
GPT-5.2 Deep₹84.00 in / ₹672.00 out per 1M tokens
GPT-5.2 Fast₹84.00 in / ₹672.00 out per 1M tokens
GPT-5.2 Max₹84.00 in / ₹672.00 out per 1M tokens

Features and tool support

TokenBazaar’s exposed interface, not every feature advertised by the provider. “Available” describes the implemented interface, not a successful test of every input or tool.

Reasoning configuration

The catalog version determines the requested reasoning effort.

Selected effort: medium (default catalog version). Reasoning level is not a measured intelligence or speed score.

Coding and agent workflows

Text/code generation and customer-managed tool loops.

Coding benchmark results do not establish a hosted terminal, sandbox, autonomous browser or guaranteed task success.

Streaming answers

Available

Incremental text through TokenBazaar’s chat endpoint; Claude also has native Messages access.

Customer-defined function tools

Limited

Only customer-defined function tools are forwarded. Model/protocol compatibility applies; your application authorizes and executes every tool.

Forced or named tool selection

Limited

The chat route accepts auto, none and required. A named-tool choice is not forwarded; exact model compatibility is not independently tested.

Images and PDFs

Not verified

The chat bridge accepts image/PDF content. Provider input modalities are listed separately; file size, content and model limits still apply.

Hosted web search / browsing

Not exposed

No provider-hosted web search or web-fetch tool is exposed. Customer-owned search can be implemented as an authorized function tool.

Hosted code execution / computer use

Not exposed

No built-in execution environment or computer-control tool is provided. Code generation is not code execution.

Hosted file search / persistent assistants

Not exposed

No hosted file-search index, Assistants endpoint or persistent provider agent is exposed.

Batch / fine-tuning / cached-price discounts

Not exposed

No public batch or fine-tuning endpoint, or separate cached-token discount, is offered here.

Sources and verification

Provider specifications describe the upstream model, not a guarantee of every feature through TokenBazaar. Prices come from the enabled catalog; benchmark results belong to the exact tested model.

Research notes (1)
  • Published provider limits; maximum-capacity requests have not been independently exercised through TokenBaazar. Thinking-level variants use the same provider model; reasoning and answer tokens share the output budget.