Models / GPT-5.2
GPT-5.2
GPT-5.2 is strongest at reasoning and knowledge; most buyers will do better with one of the alternatives below. The cheapest model of similar intelligence is MiMo-V2.6-Flash, at $0.18 per million tokens against $4.81.
Superseded. GPT-5.5 is OpenAI's newer model in this line, at $11.25 blended: see GPT-5.5 or compare the two.
Results 16 Nov 2026 · 101 results · 10 sources
Test GPT-5.2 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
- 30.4
Artificial Analysis, at xhigh reasoning; 17.0–30.4 across 3 settings - Spring Prompt overall
- Not ranked yet
needs our benchmarks and two groups of results - Developer
- OpenAI, based in the US
Weights not published - Released
- 11 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.
| Among | Intelligence Index | Spring Prompt overall | Price, blended | Speed |
|---|---|---|---|---|
| Models available today | 50th of 185Claude Opus 5.5 | – | $4.81 blended, 88th percentilecheapest: Mistral Nemo | – |
| Models priced $3–10 per million tokens | 22nd of 38Claude Opus 5.5 | – | sets this group | – |
| Models with similar intelligence | sets this group | – | $4.81 blended, 78th percentilecheapest: DeepSeek-V4-Flash (0731) | – |
| Models from developers based in the US | 34th 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
- CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is
- DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled
- SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending
- ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls
| Benchmark | GPT-5.2 | Rank among available | Best available |
|---|---|---|---|
| tau2-benchtau2 v1.0.1, retail: task success (pass^1) · reported | 81.6% | 2nd of 6 | Qwen3.5-397B-A17B 84.4% |
| tau2-benchtau2 v1.0.1, airline: task success (pass^1) · reported | 83.0% | 2nd of 6 | Claude Opus 4.5 84.0% |
| tau2-benchtau2 v1.0.1, telecom: task success (pass^1) · reported | 89.7% | 4th of 6 | Qwen3.5-397B-A17B 97.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4BFCL: overall accuracy · reported | 55.9% | 9th of 36 | Claude Opus 4.5 77.5% |
| OpenHands IndexOpenHands Index: average · reported | 58.8% | 10th of 31 | Claude Fable 5 81.0% |
| Artificial AnalysisArtificial Analysis: τ-bench banking · reported | 11.1% | 68th of 104 | Grok 4.6 50.7% |
| Vending-Bench 2Vending-Bench 2: money after a year · reported | $3,591 | 35th of 53 | GPT-6 Astra $15,515 |
- Microsoft STATE-Bench: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects
| Benchmark | GPT-5.2 | Rank among available | Best available |
|---|---|---|---|
| Remote Labor IndexRemote Labor Index: projects done to client standard · reported | 2.5% | 9th of 12 | GPT-6 Astra 20.8% |
- APEX-Agents: has not measured this model.
- GDP.pdf: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge
| Benchmark | GPT-5.2 | Rank among available | Best available |
|---|---|---|---|
| Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported | 30.4 | 50th of 185 | Claude Opus 5.5 57.6 |
| Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported | 37.7% | 52nd of 186 | Claude Opus 5.5 61.4% |
| Artificial AnalysisArtificial Analysis: GPQA Diamond · reported | 90.3% | 37th of 168 | GPT-6 Astra 96.3% |
WritingWhat people prefer in blind comparisons, and judged writing quality
| Benchmark | GPT-5.2 | Rank among available | Best available |
|---|---|---|---|
| Arena (formerly LMArena)Arena Text: overall · reported | 1,437 | 68th of 153 | Gemini 4 Argon 1,525 |
| UGI LeaderboardUGI: writing score · reported | 49.4 | 58th of 124 | Gemini 3.8 Flash 78.6 |
Sticking to the factsSummarising without inventing things, and factual answers
| Benchmark | GPT-5.2 | Rank among available | Best available |
|---|---|---|---|
| Vectara Hallucination LeaderboardVectara: hallucination rate · reported | 8.4% | 30th of 71 | GPT-5.4 nano 3.1% |
| Arena (formerly LMArena)Arena Text factuality: overall · reported | 1,442 | 61st of 109 | Gemini 4 Argon 1,511 |
| SimpleQA Verified (Epoch AI)SimpleQA Verified: correct answers · reported | 37.1% | 42nd of 68 | GPT-6 Astra 75.6% |
Speed under pressureGood decisions against a real clock (fast chess)
- BulletBench: has not measured this model.
Nearest alternatives
- Cheaper at similar intelligenceMiMo-V2.6-Flash$0.18 blended · Intelligence Index 37.9Compare with GPT-5.2 →
- OpenAI's newer model in this lineGPT-5.5$11.25 blended · Intelligence Index 38.4Compare with GPT-5.2 →
- Open weights at similar intelligenceMiMo-V2.6-Flash$0.18 blended · Intelligence Index 37.9Compare with GPT-5.2 →
Against GPT-5.2 at $4.81 blended, Intelligence Index 30.4. "Similar intelligence" means within 4 points or better.
Where to run it
2 hosts on OpenRouter at the standard service tier, with a median of $4.81 blended per million tokens. Cheapest first.
| Host | Quantisation | Input | Output | Blended |
|---|---|---|---|---|
| Azure | not stated | $1.75 | $14.00 | $4.81 |
| OpenAI | not stated | $1.75 | $14.00 | $4.81 |
Other service tiers, not counted above: OpenAI fast $3.50 in, $28.00 out; OpenAI flex $0.88 in, $7.00 out. Flex and batch are cheaper but slower or queued; priority and fast cost more.
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 | Claude Opus 5.5 most intelligent at $3–10 per million tokens | DeepSeek-V4-Flash (0731) 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 | $0.20 | $16.00 | $4.00 |
| Tokens a second | – | 96 | – | – | 53 |
| Intelligence Index | 30.4 | 57.6 | 34.3 | – | 51.8 |
| Spring Prompt overall | – | 82 | – | 90 | 80 |
| Rank among available models, by use case | |||||
| Product listings | – | 13th | – | 5th | 2nd |
| Decks from an analysis | – | 7th | – | 4th | 5th |
| User surveys | – | 4th | – | 1st | 3rd |
| Marketing planning | – | 9th | – | 1st | – |
| Agents and tool use | 62nd of 159 | 3rd | 43rd | – | 6th |
| Professional work | 33rd of 51 | 3rd | – | – | 9th |
| Reasoning and knowledge | 53rd of 187 | 1st | 47th | – | 6th |
| Writing | 76th of 169 | 5th | – | – | 16th |
| Sticking to the facts | 73rd of 139 | 3rd | 105th | – | 18th |
| Speed under pressure | – | – | – | 8th | 3rd |
| Side by side → | Side by side → | Side by side → | |||
Shaded figures are better than GPT-5.2's. A dash means no result.
Research and examples
Where it has been measured
22nd most intelligent of the 38 models priced $3–10 per million tokens. Among models available today, mid-field on every use case measured so far.
Artificial Analysis lists it but has not published a speed for it yet
- Arena (formerly LMArena)18 results
- Artificial Analysis22 results
- Berkeley Function Calling Leaderboard (BFCL) V416 results
- OpenHands Index6 results
- Remote Labor Index2 results
- SimpleQA Verified (Epoch AI)4 results
- tau2-bench16 results
- UGI Leaderboard12 results
- Vectara Hallucination Leaderboard4 results
- Vending-Bench 21 result
- BulletBenchNot measured
- CatalogBenchNot measured
- DeckBenchNot measured
- ROASBenchNot measured
- SurveyBenchNot measured
- APEX-AgentsNot measured
- GDP.pdfNot measured
- Microsoft STATE-BenchNot measured
Every result
101 published results from 10 sources, each in the source's own units, with the configuration that produced it.
Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 18 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Arena Document: overallArena rating, higher is better | 1,425 1,419–1,431 |
40 of 44 | GPT-5.2 | 13 Sep 2026 |
| Arena Document: overallArena rating, higher is better | 1,423 1,414–1,433 |
41 of 44 | GPT-5.2 (high reasoning) | 13 Sep 2026 |
| Arena Search: overallArena rating, higher is better | 1,162 1,156–1,167 |
25 of 34 | GPT-5.2 (arena search) | 24 Aug 2026 |
| Arena Search: overallArena rating, higher is better | 1,137 1,131–1,143 |
31 of 34 | GPT-5.2 (no reasoning, arena search) | 24 Aug 2026 |
| Arena Text factuality: overallArena rating, higher is better | 1,442 1,440–1,445 |
88 of 182 | GPT-5.2 | 2 Oct 2026 |
| Arena Text factuality: overallArena rating, higher is better | 1,442 1,438–1,445 |
91 of 182 | GPT-5.2 (high reasoning) | 2 Oct 2026 |
| Arena Text: business, management and financeArena rating, higher is better | 1,444 1,438–1,450 |
91 of 406 | GPT-5.2 | 2 Oct 2026 |
| Arena Text: business, management and financeArena rating, higher is better | 1,443 1,436–1,450 |
93 of 406 | GPT-5.2 (high reasoning) | 2 Oct 2026 |
| Arena Text: creative writingArena rating, higher is better | 1,391 1,385–1,398 |
122 of 411 | GPT-5.2 | 2 Oct 2026 |
| Arena Text: creative writingArena rating, higher is better | 1,387 1,379–1,394 |
134 of 411 | GPT-5.2 (high reasoning) | 2 Oct 2026 |
| Arena Text: expert promptsArena rating, higher is better | 1,459 1,452–1,466 |
103 of 363 | GPT-5.2 | 2 Oct 2026 |
| Arena Text: expert promptsArena rating, higher is better | 1,475 1,465–1,485 |
82 of 363 | GPT-5.2 (high reasoning) | 2 Oct 2026 |
| Arena Text: instruction followingArena rating, higher is better | 1,424 1,419–1,429 |
106 of 413 | GPT-5.2 | 2 Oct 2026 |
| Arena Text: instruction followingArena rating, higher is better | 1,427 1,421–1,433 |
98 of 413 | GPT-5.2 (high reasoning) | 2 Oct 2026 |
| Arena Text: overallArena rating, higher is better | 1,436 1,432–1,439 |
104 of 413 | GPT-5.2 | 2 Oct 2026 |
| Arena Text: overallArena rating, higher is better | 1,437 1,434–1,441 |
101 of 413 | GPT-5.2 (high reasoning) | 2 Oct 2026 |
| Arena Text: writing, literature and languageArena rating, higher is better | 1,412 1,406–1,417 |
104 of 412 | GPT-5.2 | 2 Oct 2026 |
| Arena Text: writing, literature and languageArena rating, higher is better | 1,408 1,402–1,415 |
108 of 412 | GPT-5.2 (high reasoning) | 2 Oct 2026 |
Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Artificial Analysis · reported by Artificial Analysis · 22 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better | 26.5 | 140 of 413 | GPT-5.2 (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better | 17.0 | 234 of 413 | GPT-5.2 (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better | 30.4 | 112 of 413 | GPT-5.2 (xhigh reasoning) | 20 Oct 2026 |
| Artificial Analysis: GPQA Diamond% of questions, higher is better | 86.4% | 111 of 360 | GPT-5.2 (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: GPQA Diamond% of questions, higher is better | 71.2% | 242 of 360 | GPT-5.2 (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: GPQA Diamond% of questions, higher is better | 90.3% | 63 of 360 | GPT-5.2 (xhigh reasoning) | 20 Oct 2026 |
| Artificial Analysis: Humanity's Last Exam% of questions, higher is better | 26.7% | 173 of 419 | GPT-5.2 (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: Humanity's Last Exam% of questions, higher is better | 8.0% | 298 of 419 | GPT-5.2 (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: Humanity's Last Exam% of questions, higher is better | 37.7% | 103 of 419 | GPT-5.2 (xhigh reasoning) | 20 Oct 2026 |
| Artificial Analysis: IFBench% of instructions, higher is better | 65.2% | 87 of 288 | GPT-5.2 (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: IFBench% of instructions, higher is better | 47.4% | 153 of 288 | GPT-5.2 (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: IFBench% of instructions, higher is better | 75.4% | 28 of 288 | GPT-5.2 (xhigh reasoning) | 20 Oct 2026 |
| Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better | 70.3% | 195 of 407 | GPT-5.2 (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better | 45.7% | 293 of 407 | GPT-5.2 (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better | 82.7% | 32 of 407 | GPT-5.2 (xhigh reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better | 43.2% | 40 of 282 | GPT-5.2 (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better | 31.8% | 97 of 282 | GPT-5.2 (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better | 47.0% | 26 of 282 | GPT-5.2 (xhigh reasoning) | 20 Oct 2026 |
| Artificial Analysis: τ-bench banking% of tasks, higher is better | 11.1% | 119 of 175 | GPT-5.2 (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: τ²-bench telecom% of tasks, higher is better | 74.3% | 116 of 286 | GPT-5.2 (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: τ²-bench telecom% of tasks, higher is better | 46.5% | 168 of 286 | GPT-5.2 (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: τ²-bench telecom% of tasks, higher is better | 84.8% | 81 of 286 | GPT-5.2 (xhigh reasoning) | 20 Oct 2026 |
Not shown: Not business work, and a blend: read the parts for any one task.
Berkeley Function Calling Leaderboard (BFCL) V4 · reported by Berkeley Function Calling Leaderboard (BFCL) V4 · 16 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| BFCL: irrelevance detection% correct, higher is better | 79.4% | 61 of 109 | GPT-5.2 (bfcl fc) | 16 Dec 2025 |
| BFCL: irrelevance detection% correct, higher is better | 87.3% | 21 of 109 | GPT-5.2 (bfcl prompt) | 16 Dec 2025 |
| BFCL: memory% correct, higher is better | 45.8% | 13 of 109 | GPT-5.2 (bfcl fc) | 16 Dec 2025 |
| BFCL: memory% correct, higher is better | 3.9% | 92 of 109 | GPT-5.2 (bfcl prompt) | 16 Dec 2025 |
| BFCL: multi-turn tasks% correct, higher is better | 28.1% | 42 of 109 | GPT-5.2 (bfcl fc) | 16 Dec 2025 |
| BFCL: multi-turn tasks% correct, higher is better | 43.8% | 24 of 109 | GPT-5.2 (bfcl prompt) | 16 Dec 2025 |
| BFCL: overall accuracy% correct, higher is better | 55.9% | 16 of 109 | GPT-5.2 (bfcl fc) | 16 Dec 2025 |
| BFCL: overall accuracy% correct, higher is better | 45.3% | 38 of 109 | GPT-5.2 (bfcl prompt) | 16 Dec 2025 |
| BFCL: relevance detection% correct, higher is better | 75.0% | 62 of 109 | GPT-5.2 (bfcl fc) | 16 Dec 2025 |
| BFCL: relevance detection% correct, higher is better | 75.0% | 62 of 109 | GPT-5.2 (bfcl prompt) | 16 Dec 2025 |
| BFCL: single-turn calls (curated)% correct, higher is better | 81.9% | 67 of 109 | GPT-5.2 (bfcl fc) | 16 Dec 2025 |
| BFCL: single-turn calls (curated)% correct, higher is better | 78.3% | 79 of 109 | GPT-5.2 (bfcl prompt) | 16 Dec 2025 |
| BFCL: single-turn calls (user-contributed)% correct, higher is better | 70.4% | 58 of 109 | GPT-5.2 (bfcl fc) | 16 Dec 2025 |
| BFCL: single-turn calls (user-contributed)% correct, higher is better | 67.1% | 73 of 109 | GPT-5.2 (bfcl prompt) | 16 Dec 2025 |
| BFCL: web search% correct, higher is better | 75.5% | 10 of 109 | GPT-5.2 (bfcl fc) | 16 Dec 2025 |
| BFCL: web search% correct, higher is better | 40.5% | 30 of 109 | GPT-5.2 (bfcl prompt) | 16 Dec 2025 |
Not shown: Not general refusal or safety behaviour.
OpenHands Index · reported by OpenHands Index · 6 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| OpenHands Index: average% resolved, higher is better | 58.8% | 10 of 34 | GPT-5.2 (openhands) | 30 Jun 2026 |
| OpenHands Index: front end (SWE-Bench Multimodal)% resolved, higher is better | 30.9% | 20 of 34 | GPT-5.2 (openhands) | 30 Jun 2026 |
| OpenHands Index: greenfield (Commit0)% resolved, higher is better | 50.0% | 6 of 34 | GPT-5.2 (openhands) | 30 Jun 2026 |
| OpenHands Index: information gathering (GAIA)% resolved, higher is better | 65.5% | 16 of 34 | GPT-5.2 (openhands) | 30 Jun 2026 |
| OpenHands Index: issue resolution (SWE-Bench)% resolved, higher is better | 74.6% | 13 of 34 | GPT-5.2 (openhands) | 30 Jun 2026 |
| OpenHands Index: testing (SWT-Bench)% resolved, higher is better | 73.2% | 10 of 34 | GPT-5.2 (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.
Remote Labor Index · reported by Remote Labor Index · 2 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Remote Labor Index: projects done to client standard% of projects, higher is better | 2.1% | 10 of 14 | GPT-5.2 | 1 Oct 2026 |
| Remote Labor Index: projects done to client standard% of projects, higher is better | 2.5% | 9 of 14 | GPT-5.2 (medium reasoning) | 1 Oct 2026 |
Not shown: Not speed or cost; a small set of projects, so a few points either way are noise.
SimpleQA Verified (Epoch AI) · reported by SimpleQA Verified (Epoch AI) · 4 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| SimpleQA Verified: correct answers% of questions, higher is better | 34.3% | 51 of 85 | GPT-5.2 (high reasoning) | 27 Aug 2026 |
| SimpleQA Verified: correct answers% of questions, higher is better | 32.8% | 59 of 85 | GPT-5.2 (low reasoning) | 27 Aug 2026 |
| SimpleQA Verified: correct answers% of questions, higher is better | 32.7% | 61 of 85 | GPT-5.2 (medium reasoning) | 27 Aug 2026 |
| SimpleQA Verified: correct answers% of questions, higher is better | 37.1% | 47 of 85 | GPT-5.2 (xhigh reasoning) | 27 Aug 2026 |
Not shown: Not answers grounded in your documents; tests what the model remembers.
tau2-bench · reported by tau2-bench · 16 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| tau2 v1.0.1, airline: consistency (pass^4)% of tasks, higher is better | 72.0% | 1 of 8 | GPT-5.2 (high reasoning, tau2) | 5 May 2026 |
| tau2 v1.0.1, airline: consistency (pass^4)% of tasks, higher is better | 22.0% | 8 of 8 | GPT-5.2 (no reasoning, tau2) | 26 May 2026 |
| tau2 v1.0.1, airline: task success (pass^1)% of tasks, higher is better | 83.0% | 2 of 8 | GPT-5.2 (high reasoning, tau2) | 5 May 2026 |
| tau2 v1.0.1, airline: task success (pass^1)% of tasks, higher is better | 52.5% | 8 of 8 | GPT-5.2 (no reasoning, tau2) | 26 May 2026 |
| tau2 v1.0.1, banking knowledge, alltools retrieval: consistency (pass^4)% of tasks, higher is better | 18.6% | 11 of 21 | GPT-5.2 (high reasoning, tau2) | 5 May 2026 |
| tau2 v1.0.1, banking knowledge, alltools retrieval: task success (pass^1)% of tasks, higher is better | 32.2% | 13 of 21 | GPT-5.2 (high reasoning, tau2) | 5 May 2026 |
| tau2 v1.0.1, banking knowledge, qwen_embeddings retrieval: consistency (pass^4)% of tasks, higher is better | 4.1% | 1 of 1 | GPT-5.2 (no reasoning, tau2) | 26 May 2026 |
| tau2 v1.0.1, banking knowledge, qwen_embeddings retrieval: task success (pass^1)% of tasks, higher is better | 12.6% | 1 of 1 | GPT-5.2 (no reasoning, tau2) | 26 May 2026 |
| tau2 v1.0.1, retail: consistency (pass^4)% of tasks, higher is better | 51.8% | 2 of 8 | GPT-5.2 (high reasoning, tau2) | 5 May 2026 |
| tau2 v1.0.1, retail: consistency (pass^4)% of tasks, higher is better | 45.6% | 6 of 8 | GPT-5.2 (no reasoning, tau2) | 26 May 2026 |
| tau2 v1.0.1, retail: task success (pass^1)% of tasks, higher is better | 81.6% | 2 of 8 | GPT-5.2 (high reasoning, tau2) | 5 May 2026 |
| tau2 v1.0.1, retail: task success (pass^1)% of tasks, higher is better | 75.0% | 6 of 8 | GPT-5.2 (no reasoning, tau2) | 26 May 2026 |
| tau2 v1.0.1, telecom: consistency (pass^4)% of tasks, higher is better | 71.9% | 4 of 8 | GPT-5.2 (high reasoning, tau2) | 5 May 2026 |
| tau2 v1.0.1, telecom: consistency (pass^4)% of tasks, higher is better | 30.7% | 8 of 8 | GPT-5.2 (no reasoning, tau2) | 26 May 2026 |
| tau2 v1.0.1, telecom: task success (pass^1)% of tasks, higher is better | 89.7% | 5 of 8 | GPT-5.2 (high reasoning, tau2) | 5 May 2026 |
| tau2 v1.0.1, telecom: task success (pass^1)% of tasks, higher is better | 57.2% | 8 of 8 | GPT-5.2 (no reasoning, tau2) | 26 May 2026 |
Not shown: Not your policies or customers: the tasks and policies are tau2's own, and the customer is simulated by gpt-5.2.
UGI Leaderboard · reported by UGI Leaderboard · 12 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| UGI: requested-length error% off the requested word count, lower is better | 76.0% | 343 of 379 | GPT-5.2 (high reasoning) | 4 Mar 2026 |
| UGI: requested-length error% off the requested word count, lower is better | 103.0% | 359 of 379 | GPT-5.2 (low reasoning) | 4 Mar 2026 |
| UGI: requested-length error% off the requested word count, lower is better | 93.0% | 354 of 379 | GPT-5.2 (medium reasoning) | 4 Mar 2026 |
| UGI: requested-length error% off the requested word count, lower is better | 112.0% | 364 of 379 | GPT-5.2 (no reasoning) | 4 Mar 2026 |
| UGI: style adherencescore from 0 to 1, higher is better | 0.38 | 65 of 379 | GPT-5.2 (high reasoning) | 4 Mar 2026 |
| UGI: style adherencescore from 0 to 1, higher is better | 0.40 | 34 of 379 | GPT-5.2 (low reasoning) | 4 Mar 2026 |
| UGI: style adherencescore from 0 to 1, higher is better | 0.37 | 95 of 379 | GPT-5.2 (medium reasoning) | 4 Mar 2026 |
| UGI: style adherencescore from 0 to 1, higher is better | 0.38 | 68 of 379 | GPT-5.2 (no reasoning) | 4 Mar 2026 |
| UGI: writing scorescore out of 100, higher is better | 49.4 | 168 of 379 | GPT-5.2 (high reasoning) | 4 Mar 2026 |
| UGI: writing scorescore out of 100, higher is better | 43.9 | 194 of 379 | GPT-5.2 (low reasoning) | 4 Mar 2026 |
| UGI: writing scorescore out of 100, higher is better | 44.1 | 191 of 379 | GPT-5.2 (medium reasoning) | 4 Mar 2026 |
| UGI: writing scorescore out of 100, higher is better | 39.2 | 229 of 379 | GPT-5.2 (no reasoning) | 4 Mar 2026 |
Not shown: Not other format limits such as character counts or bullet counts.
Vectara Hallucination Leaderboard · reported by Vectara Hallucination Leaderboard · 4 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Vectara: answer rate% of documents, higher is better | 100.0% | 1 of 108 | GPT-5.2 (high reasoning) | 22 Sep 2026 |
| Vectara: answer rate% of documents, higher is better | 100.0% | 1 of 108 | GPT-5.2 (low reasoning) | 22 Sep 2026 |
| Vectara: hallucination rate% of summaries, lower is better | 10.8% | 68 of 108 | GPT-5.2 (high reasoning) | 22 Sep 2026 |
| Vectara: hallucination rate% of summaries, lower is better | 8.4% | 43 of 108 | GPT-5.2 (low reasoning) | 22 Sep 2026 |
Not shown: Not a quality score: a low rate usually means content filters were triggered, and hallucination rates are measured on answered documents only.
Vending-Bench 2 · reported by Vending-Bench 2 · 1 result
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Vending-Bench 2: money after a yearUS dollars, higher is better | $3,591 | 41 of 63 | GPT-5.2 | 1 Oct 2026 |
Not shown: Not a real business; one simulated market with set rules.
Will GPT-5.2 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.