Models / GPT-5.2-Codex

OpenAI

GPT-5.2-Codex

Early evidence, 13 results from 2 sources, on 2 use cases. GPT-5.2-Codex is strongest at reasoning and knowledge; there is too little evidence yet to recommend it either way. The cheapest model of similar intelligence is MiMo-V2.6-Flash, at $0.18 per million tokens against $4.81.

Superseded. GPT-5.3-Codex is OpenAI's newer model in this line, at $4.81 blended: see GPT-5.3-Codex.

Results 16 Nov 2026 · 13 results · 2 sources

Test GPT-5.2-Codex on your prompt → It runs beside the models you could use instead, with every answer checked and costed.

Price per million tokens
$1.75 in · $14.00 out
Typical host on OpenRouter, 10 Nov 2026 · compare prices
Speed
Not measured
Intelligence Index
28.5
Artificial Analysis, at xhigh reasoning
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
OpenAI, based in the US
Weights not published
Released
18 Dec 2025
400,000 tokens of context

Where it stands among the models you could choose

Available models grouped by price, intelligence, speed and developer location. Retired models are excluded.

AmongIntelligence IndexSpring Prompt overallPrice, blendedSpeed
Models available today 58th of 185Claude Opus 5.5 – $4.81 blended, 88th percentilecheapest: Mistral Nemo –
Models priced $3–10 per million tokens 25th of 38Claude Opus 5.5 – sets this group –
Models with similar intelligence sets this group – $4.81 blended, 82nd percentilecheapest: Nemotron 3.5 Super VL –
Models from developers based in the US 38th of 92Claude Opus 5.5 – $4.81 blended, 77th percentilecheapest: Gemma 3 4B –

The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.

How good is it, and for what?

Each use case ranks the available models its benchmarks measured, then those priced $3–10 per million tokens. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.

Product listingsTurning a sparse product feed and photos into listings that can go live Not measured
  • CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is Not measured
  • DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled Not measured
  • SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending Not measured
  • ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 55th of 159 available · 25th of 35 at its price
BenchmarkGPT-5.2-CodexRank among availableBest available
OpenHands IndexOpenHands Index: average · reported 58.3% 11th of 31 Claude Fable 5 81.0%
  • tau2-bench: has not measured this model.
  • Berkeley Function Calling Leaderboard (BFCL) V4: pending. Its latest results are dated 16 Dec 2025, before this model was released.
  • Microsoft STATE-Bench: has not measured this model.
  • Artificial Analysis: has not measured this model.
  • Vending-Bench 2: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects Not measured
  • APEX-Agents: has not measured this model.
  • GDP.pdf: has not measured this model.
  • Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge 58th of 187 available · 25th of 39 at its price
BenchmarkGPT-5.2-CodexRank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 28.5 58th of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 35.7% 57th of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 89.9% 40th of 168 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality Not measured
  • Arena (formerly LMArena): has not measured this model.
  • UGI Leaderboard: has not measured this model.
Sticking to the factsSummarising without inventing things, and factual answers Not measured
  • Vectara Hallucination Leaderboard: has not measured this model.
  • Arena (formerly LMArena): has not measured this model.
  • SimpleQA Verified (Epoch AI): has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess) Not measured
  • BulletBench: has not measured this model.

Nearest alternatives

  • Cheaper at similar intelligenceMiMo-V2.6-Flash$0.18 blended · Intelligence Index 37.9
  • OpenAI's newer model in this lineGPT-5.3-Codex$4.81 blended · Intelligence Index 32.5
  • Open weights at similar intelligenceMiMo-V2.6-Flash$0.18 blended · Intelligence Index 37.9

Against GPT-5.2-Codex at $4.81 blended, Intelligence Index 28.5. "Similar intelligence" means within 4 points or better.

Where to run it

1 host on OpenRouter at the standard service tier, with a median of $4.81 blended per million tokens. Cheapest first.

HostQuantisationInputOutputBlended
Azurenot stated$1.75$14.00$4.81

Prices per million tokens from OpenRouter's public endpoint list, checked 10 Nov 2026.

Against the alternatives

The models you would most likely weigh it against: the leaders of the groups above.

Scroll sideways to see every alternative.

GPT-5.2-CodexClaude Opus 5.5
most intelligent at $3–10 per million tokens
Nemotron 3.5 Super VL
cheapest with similar intelligence
Claude Fable 5.2
leads overall
GPT-6.1 Sol
OpenAI's best other model
Price per million tokens $4.81 $8.00$0.24$16.00$4.00
Tokens a second – 96411–53
Intelligence Index 28.5 57.626.5–51.8
Spring Prompt overall – 82–9080
Rank among available models, by use case
Product listings – 13th–5th2nd
Decks from an analysis – 7th–4th5th
User surveys – 4th–1st3rd
Marketing planning – 9th–1st–
Agents and tool use 55th of 159 3rd132nd–6th
Professional work – 3rd––9th
Reasoning and knowledge 58th of 187 1st74th–6th
Writing – 5th––16th
Sticking to the facts – 3rd––18th
Speed under pressure – ––8th3rd

Shaded figures are better than GPT-5.2-Codex's. A dash means no result.

Where it has been measured

25th most intelligent of the 38 models priced $3–10 per million tokens. Among models available today, mid-field on agents and tool use, and reasoning and knowledge, the use cases measured so far.

Artificial Analysis lists it but has not published a speed for it yet

Every result

13 published results from 2 sources, each in the source's own units, with the configuration that produced it.

Artificial Analysis · reported by Artificial Analysis · 7 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 28.5 125 of 413 GPT-5.2-Codex (xhigh reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 89.9% 67 of 360 GPT-5.2-Codex (xhigh reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 35.7% 114 of 419 GPT-5.2-Codex (xhigh reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 77.6% 13 of 288 GPT-5.2-Codex (xhigh reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 82.3% 37 of 407 GPT-5.2-Codex (xhigh reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 37.1% 67 of 282 GPT-5.2-Codex (xhigh reasoning) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 92.1% 46 of 286 GPT-5.2-Codex (xhigh reasoning) 20 Oct 2026

Not shown: Not business work, and a blend: read the parts for any one task.

OpenHands Index · reported by OpenHands Index · 6 results
MeasureValueRankConfigurationDated
OpenHands Index: average% resolved, higher is better 58.3% 11 of 34 GPT-5.2-Codex (openhands) 30 Jun 2026
OpenHands Index: front end (SWE-Bench Multimodal)% resolved, higher is better 35.9% 16 of 34 GPT-5.2-Codex (openhands) 30 Jun 2026
OpenHands Index: greenfield (Commit0)% resolved, higher is better 43.8% 8 of 34 GPT-5.2-Codex (openhands) 30 Jun 2026
OpenHands Index: information gathering (GAIA)% resolved, higher is better 70.9% 12 of 34 GPT-5.2-Codex (openhands) 30 Jun 2026
OpenHands Index: issue resolution (SWE-Bench)% resolved, higher is better 73.8% 19 of 34 GPT-5.2-Codex (openhands) 30 Jun 2026
OpenHands Index: testing (SWT-Bench)% resolved, higher is better 67.0% 20 of 34 GPT-5.2-Codex (openhands) 30 Jun 2026

Not shown: Not the model alone: the score is for the model inside the OpenHands agent, at the SDK version shown.

Will GPT-5.2-Codex work for your product?

Benchmarks aren't your task. Paste the prompt your product uses and run it beside the models you could use instead, with every answer checked and costed.

New here? Your email starts a free trial. No credit card needed.