GPT-5.2 (2025-12-11)
Dec 2025
GPT-5.2 (2025-12-11)Compare inon
Benchmarks of GPT-5.2 (2025-12-11)26
BenchmarkByScoreRank
Knowledge2
Reasoning1
Math4
Agents2
Legacy · saturated or no longer reported17
No benchmark matches
Rankingat xhigh effort?
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperGemini 3.1 Pro Previewunstated-11%-6%$2 / $12Cannot use both thinking controls
BetterClaude Opus 4.8max+66%+108%$4.08
OpenKimi K2.6unstated-22%-64%$0.95 / $4Context: 400K → 256K
CheaperMuse Sparkunstated-22%-58%$1.25 / $4.25Only n=1 · Meta / Chat Completions+1
CheaperGLM 5.1unstatedOpen-34%-55%$1.40 / $4.40Context: 400K → 203K+1ModelScoreCostPer taskWhat changes
Gemini 3.1 Pro Previewunstated-11%-6%$2 / $12Cannot use both thinking controlsMuse Sparkunstated-22%-58%$1.25 / $4.25Only n=1 · Meta / Chat Completions+1Kimi K2.6unstatedOpen-22%-64%$0.95 / $4Context: 400K → 256KGLM 5.1unstatedOpen-34%-55%$1.40 / $4.40Context: 400K → 203K+1GPT-5 (2025-08-07)high-34%-29%$1.25 / $10ModelScoreCostPer taskWhat changes
Claude Opus 4.8max+66%+108%$4.08GPT-5.4 (2026-03-05)xhigh+44%+17%$2.50 / $15Claude Opus 4.7xhigh+22%+108%$5 / $25Claude Opus 4.6max+22%+108%$5 / $25ModelScoreCostPer taskWhat changes
Kimi K2.6unstatedOpen-22%-64%$0.95 / $4Context: 400K → 256KGLM 5.1unstatedOpen-34%-55%$1.40 / $4.40Context: 400K → 203K+1GLM-4.6unstatedOpen-89%-79%$0.60 / $2.20Context: 400K → 200K+1GLM 5unstatedOpen-89%-68%$1 / $3.20Context: 400K → 203K+1Kimi K2 ThinkingunstatedOpen-100%-82%$0.47 / $2Context: 400K → 256K+1ModelScoreCostPer taskWhat changes
GPT-5.4 (2026-03-05)xhigh+44%—$2.50 / $15GPT-5 Pro (2025-10-06)-22%—$15 / $120GPT-5.4 Nano (2026-03-17)high-67%—$0.20 / $1.25GPT-5 (2025-08-07)medium-67%—$1.25 / $10GPT-5.1 (2025-11-13)medium-78%—$1.25 / $10GPT-5 Mini (2025-08-07)medium-78%—$0.25 / $2GPT-5 Nano (2025-08-07)medium-89%—$0.05 / $0.40o3 (2025-04-16)high-89%—$2 / $8Context: 400K → 200KAll OpenAI models →History
17 versionsBenchmarks
all categoriesChat & Knowledge
SimpleQA Verified v137.1#44
FrontierMath40.7#5
FrontierMath Tier 418.8#5
FrontierMath Tiers 1–3 (v2)67.4#27
FrontierMath Tier 4 (v2)31.7#28
Chess Puzzles48#15
GPQA Diamond · Epoch91.4#22
OTIS Mock AIME 2024 202596.1#30
Coding
SWE-rebench · all · 2025-12-01 to 2026-02-0156.6#1
SWE-rebench · Go · 2025-12-01 to 2026-02-010#1
SWE-rebench · Java · 2025-12-01 to 2026-02-010#1
SWE-rebench · Rust · 2025-12-01 to 2026-02-010#1
SWE-rebench · Python · 2025-12-01 to 2026-02-0156.6#1
SWE-rebench · TypeScript · 2025-12-01 to 2026-02-010#1
Agents & Tool Use
EBR Bench23#16
Furniture Assembly38.3#18
FAQ
How much does GPT-5.2 (2025-12-11) cost?›
$1.75 per 1M input tokens and $14 per 1M output tokens.
Is GPT-5.2 (2025-12-11) free to use?›
There is no free API; the cheapest paid price is $1.75 per 1M input tokens.
How good is GPT-5.2 (2025-12-11), and what is it best at?›
#44 of 83 in Chat & Knowledge, #14 of 24 in Coding, #7 of 39 in Agents & Tool Use.
Is GPT-5.2 (2025-12-11) better than Claude Opus 4.6?›
On FrontierMath Tier 4, GPT-5.2 (2025-12-11) scores 18.8 vs 22.9 — lower.
How can I use GPT-5.2 (2025-12-11)?›
Through the OpenAI API.
What is the context window of GPT-5.2 (2025-12-11)?›
400K tokens.
When was GPT-5.2 (2025-12-11) released? Is there a newer version?›
Released 2025-12-11. It is the current version in its line.
Can GPT-5.2 (2025-12-11) read images?›
It accepts text and images as input.
What is GPT-5.2 (2025-12-11)?›
GPT-5.2 (2025-12-11) is a language model from OpenAI, released Dec 2025.
What are the best alternatives to GPT-5.2 (2025-12-11)?›
Gemini 3.1 Pro Preview (cheaper), Claude Opus 4.8 (better), Kimi K2.6 (open weights).