Skip to content
Bencher

Models · OpenAI · Out sinceReleased 10 Dec 2025

GPT-5.2

Available on OpenRouterOn OpenRouterAvailable nowGenerally availableClosed (can't be downloaded)Proprietary

GPT-5.2 is made by OpenAI. We don't have enough test results yet to rank it. It's mid-priced to use.

Auto-created from OpenRouter catalog; verify details.

Writing & creativity
—
Research & analysis
—
Coding
—
Price
Mid-priced$1.75 / $14
Price per 1M (blended)Blended / 1M
$4.81
MemoryContext
400K
Longest answerMax output
—
Test resultsResults
9 (9 independent9 indep.)
Out sinceReleased
10 Dec 2025
Made byVendor
OpenAI
UnderstandsInputs
—

Scores are out of 100 for each area, compared with every model we track; “#” is its rank. Context is how much text it can read at once (1M is roughly 700,000 words). Blended price mixes the cost of what you send and what it writes back.

Thinking levels

Reasoning settings

You can't choose how long this one thinks.

No adjustable reasoning setting listed.

Read more

Links

Using it through OpenRouter

On OpenRouter

OpenRouter is a service that gives access to many AI models in one place. This model is listed there as openai/gpt-5.2.

Route it as openai/gpt-5.2 at $1.75 in / $14 out per 1M tokens, 400K context. Listed since 10 Dec 2025.

include_reasoningmax_completion_tokensmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstool_choicetools

Every test result

Every result

All the numbers,with where they came from.

Every result we've found for this model, with who measured it and a link to where we read it.

All raw rows (vendor and independent kept separate), with setting label, source, date, harness and notes.

All results for this model
NotesNotes
GPQA Diamond91.7%Extra highreasoning_effort=xhighIndependent testIndependentVals.ai ↗1 Sep 2026—±1.837 stderr; $0.149/test
LMArena Search Arena1207Defaultgpt-5.2-searchIndependent testIndependentLMArena ↗24 Aug 2026—rank 11 (rank range 8-16); 95% CI 1201.3-1212.5; 52712 votes
MCP Atlas67.6%Extra highgpt-5.2 (xhigh)Independent testIndependentScale AI SEAL ↗1 Oct 2026—rank 17 (Scale rank accounts for CI); ±2.9; entry added 2025-09-10
METR 50% time horizon5.9 hDefaultIndependent testIndependentMETR ↗8 May 2026METR react agent (Inspect)50% time horizon, METR-Horizon-v1.1; 95% CI 198-815 min; 80% horizon 66.0 min; release 2025-12-11; raw data https://metr.org/assets/benchmark_results_1_1.yaml
SWE-bench Multilingual66.7%HighIndependent testIndependentSWE-bench ↗13 Feb 2026mini-SWE-agent 2.0.0a0Official SWE-bench bash-only (mini-SWE-agent) run; data file https://raw.githubusercontent.com/SWE-bench/swe-bench.github.io/master/data/leaderboards.json; leaderboard not updated since 2026-02-26
SWE-Bench Pro (private/commercial set)23.8%DefaultGPT 5.2Independent testIndependentScale AI SEAL ↗1 Oct 2026—rank 7 (Scale rank accounts for CI); ±5.09; entry added 2026-01-12
SWE-Bench Pro (public, v1)29.9%Defaultgpt-5.2Independent testIndependentScale AI SEAL ↗1 Oct 2026—rank 16 (Scale rank accounts for CI); ±2.15; entry added 2026-01-27
SWE-bench Verified (bash-only, mini-SWE-agent)72.8%HighIndependent testIndependentSWE-bench ↗17 Feb 2026mini-SWE-agent 2.0.0Official SWE-bench bash-only (mini-SWE-agent) run; data file https://raw.githubusercontent.com/SWE-bench/swe-bench.github.io/master/data/leaderboards.json; leaderboard not updated since 2026-02-26
Vals TaxEval v275.8%Extra highreasoning_effort=xhighIndependent testIndependentVals.ai ↗1 Sep 2026—vals id openai/gpt-5.2-2025-12-11; rank 11/145; ±0.845 stderr; $0.066435/test