New: GPT-6.2 benchmark report is here.Read the report ↗

Explore GPT-6.2 Sol’s published benchmark results and provider offerings below. More comparable task results are needed to describe its strongest areas.

Updated: Data as of:

Strongest results

Strongest results for GPT-6.2 Sol in tracked evaluation cohorts
BenchmarkMeasuresScore
Artificial Analysis Intelligence Index ↗5.0.1 / Artificial AnalysisGeneral intelligence57 pointsJoint #5 of 11

Model details

Proprietary20 benchmarks
Specifications for GPT-6.2 Sol
ModelGPT-6.2 Sol
Agent Index v1.3Insufficient coverage (0/7) · Preview
CreatorOpenAI (opens in a new tab)
AvailabilityProprietary
Context size1,050,000 tokens (opens in a new tab)
Max output128,000 tokens (opens in a new tab)
Knowledge cutoff2026-06-01
LicenseNot reported

Pricing and performance

Per provider and reported configuration. Prices are USD per 1M tokens.

Provider offerings for GPT-6.2 Sol
Provider / configurationContexttokensInputUSD / 1M tokensOutputUSD / 1M tokensLatencyTTFT · secondsSpeedtokens / sec
Standard API1,050,000$2.00 (opens in a new tab)$10.00 (opens in a new tab)Not reportedNot reported

Blended token cost

USD per 1M tokens · 50% input + 50% output · lower is better

GPT-6.2 Sol highlighted10 of 49 priced models selected
Pricing details and sources

Blended cost = (input price + output price) ÷ 2: 500,000 input and 500,000 output tokens. Each model uses its lowest sourced current provider rate, excluding batch and Flex tiers. Cache discounts, tool fees and workload-specific token usage are excluded. 52 models without complete sourced current prices are unavailable in this comparison. The default selection is this model and the nine closest in blended cost; if this model has no price, we show the ten cheapest. The scale stays fixed across pages of your selection.

Pricing sources for selected models
ModelInput / 1MOutput / 1MBlended / 1MProvider / source
Grok 4.7$2.00$6.00$4.00SpaceXAIGrok 4.7 (xhigh) · Checked 2026-11-02
Gemini 4 Hydrogen$1.50$7.50$4.50Google ↗Standard Gemini API; independent speed measured at xhigh · Checked 2026-11-12
Claude Sonnet 5$2.00$10.00$6.00AmazonClaude Sonnet 5 (max) · Checked 2026-11-02
Claude Sonnet 5.5$2.00$10.00$6.00AmazonClaude Sonnet 5.5 (max with fallback) · Checked 2026-11-02
GPT-6.1 Sol$2.00$10.00$6.00AzureGPT-6.1 Sol (max) · Checked 2026-11-02
GPT-6.2 Sol$2.00$10.00$6.00OpenAI ↗Standard API · Checked 2026-11-17
Kimi K3.1 Pro$2.00$10.00$6.00KimiKimi K3.1 Pro · Checked 2026-11-02
Gemini 3.1 Pro$2.00$12.00$7.00Google (AI Studio)Gemini 3.1 Pro Preview (AI Studio) · Checked 2026-11-02
GPT-5.6 Terra$2.00$12.00$7.00OpenAI ↗Standard API, prompts up to 272K input tokens · Checked 2026-11-02
Kimi K3$0.65$15.00$7.825MakoraKimi K3 (max) · Checked 2026-11-02

Output speed

Output tokens per second · higher is better

No sourced output speed for GPT-6.2 Sol.10 of 34 models with reports selected
Measurement details and sources

Output speed measures generated tokens per second. Each model uses its fastest sourced current provider report. Batch and Flex tiers are excluded. Provider, configuration, prompt and reporting methods can differ, so these are reported observations rather than controlled head-to-head tests. 67 models have no qualifying sourced speed report. Defaults include this model and the nine closest reported values, or the ten leading models if this model has no report. The scale stays fixed across selected pages.

Output speed sources for selected models
ModelOutput speedProvider / configurationMeasurementSource
DeepSeek V4.1 Flash 10171,075.275 t/sInco (FAST)DeepSeek V4.1 Flash 1017 (max) (FAST)longmedianArtificial Analysis: DeepSeek V4.1 Flash 1017 (max) (FAST); host Inco (FAST); standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record.SourceChecked 2026-11-02
DeepSeek V4.1 Flash830.034 t/sBaseten (FAST)DeepSeek V4.1 Flash (max) (FAST)longmedianArtificial Analysis: DeepSeek V4.1 Flash (max) (FAST); host Baseten (FAST); standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record.SourceChecked 2026-11-02
MiniMax M3.1 Flash812.597 t/sIncoMiniMax-M3.1-FlashlongmedianArtificial Analysis: MiniMax-M3.1-Flash; host Inco; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record.SourceChecked 2026-11-02
GLM-5.3688.217 t/sSystalyzeGLM-5.3 (max)longmedianArtificial Analysis: GLM-5.3 (max); host Systalyze; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record.SourceChecked 2026-11-02
Kimi K3481.694 t/sInco (FAST)Kimi K3 (max) (FAST)longmedianArtificial Analysis: Kimi K3 (max) (FAST); host Inco (FAST); standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record.SourceChecked 2026-11-02
GPT-6.1 Sol342.946 t/sOpenAI (Ultrafast)GPT-6.1 Sol (max) (Ultrafast)longmedianArtificial Analysis: GPT-6.1 Sol (max) (Ultrafast); host OpenAI (Ultrafast); standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record.SourceChecked 2026-11-02
DeepSeek V4 Pro 0813305.002 t/sSystalyzeDeepSeek V4 Pro 0813 (max)longmedianArtificial Analysis: DeepSeek V4 Pro 0813 (max); host Systalyze; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record.SourceChecked 2026-11-02
Muse Spark 1.1294.835 t/sMetaMuse Spark 1.1 (xhigh)longmedianArtificial Analysis: Muse Spark 1.1 (xhigh); host Meta; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record.SourceChecked 2026-11-02
Muse Spark 1.2277.574 t/sMetaMuse Spark 1.2 (xhigh)longmedianArtificial Analysis: Muse Spark 1.2 (xhigh); host Meta; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record.SourceChecked 2026-11-02
Gemini 4 Hydrogen198.156 t/sGoogleStandard Gemini API; independent speed measured at xhighPrompt not specifiedStatistic not specifiedOfficial standard API price; output includes thinking. Explicit caching unsupported. Independent first-party Google output-speed headline at xhigh. 41.11s is time to first answer, so it is not entered as TTFT. No region/concurrency/measurement date was reported in this summary.SourceChecked 2026-11-12

Latency

Time to first token in seconds · lower is better

No sourced time-to-first-token latency for GPT-6.2 Sol.10 of 32 models with reports selected
Measurement details and sources

Latency measures time to first token (TTFT), converted to seconds. Each model uses its lowest sourced current TTFT report; total response time is excluded. Batch and Flex tiers are excluded. Provider, configuration, prompt and reporting methods can differ, so these are reported observations rather than controlled head-to-head tests. 69 models have no qualifying sourced latency report. Defaults include this model and the nine closest reported values, or the ten leading models if this model has no report. The scale stays fixed across selected pages.

Latency sources for selected models
ModelLatencyProvider / configurationMeasurementSource
DeepSeek V4.1 Flash 10170.182 sBaseten (FAST)DeepSeek V4.1 Flash 1017 (max) (FAST)longmedianArtificial Analysis: DeepSeek V4.1 Flash 1017 (max) (FAST); host Baseten (FAST); standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record.SourceChecked 2026-11-02
DeepSeek V4.1 Flash0.311 sTogether AIDeepSeek V4.1 Flash (max)longmedianArtificial Analysis: DeepSeek V4.1 Flash (max); host Together AI; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record.SourceChecked 2026-11-02
MiniMax M3.1 Flash0.584 sTogether AIMiniMax-M3.1-FlashlongmedianArtificial Analysis: MiniMax-M3.1-Flash; host Together AI; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record.SourceChecked 2026-11-02
GLM-5.30.597 sTogether AIGLM-5.3 (max)longmedianArtificial Analysis: GLM-5.3 (max); host Together AI; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record.SourceChecked 2026-11-02
MiniMax M30.699 sMiniMaxMiniMax-M3source aggregatemedianExplicit first-party AA measurement; reasoning configuration retained. Cross-provider medians are excluded. Retrieval time is not measurement time.SourceChecked 2026-11-02
DeepSeek V4 Pro 08130.832 sDigitalOceanDeepSeek V4 Pro 0813 (max)longmedianArtificial Analysis: DeepSeek V4 Pro 0813 (max); host DigitalOcean; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record.SourceChecked 2026-11-02
Kimi K30.87 sDatabricksKimi K3 (max)longmedianArtificial Analysis: Kimi K3 (max); host Databricks; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record.SourceChecked 2026-11-02
Claude Opus 4.61.35 sAmazonClaude Opus 4.6 (non-reasoning, high)longmedianArtificial Analysis: Claude Opus 4.6 (non-reasoning, high); host Amazon; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record.SourceChecked 2026-11-02
GLM-5.3-Flash1.546 sZ.aiGLM-5.3-Flashsource aggregatemedianExplicit first-party AA measurement; reasoning configuration retained. Cross-provider medians are excluded. Retrieval time is not measurement time.SourceChecked 2026-11-02
GLM-5.21.777 sZ.aiGLM-5.2 (Max)source aggregatemedianExplicit first-party AA measurement; reasoning configuration retained. Cross-provider medians are excluded. Retrieval time is not measurement time.SourceChecked 2026-11-02

Reported benchmarks

All published results in our dataset, with versions, evaluation settings, and sources.

All published benchmark reports for GPT-6.2 Sol
BenchmarkScoreEvaluation setupSource
AA-3DOpenAI GPT-6.2 launch / blinded human preferencePreference rating · Higher is better1,259 Eloevaluation: Blinded human preference between interactive 3D experiences from the same promptOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
AAV Capsid Packaging PredictionGPT-6.2 system cardMean Spearman rank correlation · Higher is better0.574 coefficientheld out sequences: 1100 · labeled sequences: 5000 · tools: CPU container, Python, web searchOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
Agents’ Last Exam1.1 / OpenAI GPT-6.2 launchAverage rubric score · Higher is better73%cost per task usd: 1.32 · reasoning effort: maxOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
Agents’ Last Exam1.1 / OpenAI GPT-6.2 launchAverage rubric score · Higher is better72.5%cost per task usd: 0.86 · reasoning effort: xhighOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
Agents’ Last Exam1.1 / OpenAI GPT-6.2 launchAverage rubric score · Higher is better72%cost per task usd: 0.69 · reasoning effort: highOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
Agents’ Last Exam1.1 / OpenAI GPT-6.2 launchAverage rubric score · Higher is better70.3%cost per task usd: 0.57 · reasoning effort: mediumOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
Agents’ Last Exam1.1 / OpenAI GPT-6.2 launchAverage rubric score · Higher is better66.7%cost per task usd: 0.27 · reasoning effort: lowOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
Artificial Analysis Intelligence Index5.0.1 / Artificial AnalysisIndex score · Higher is better57 pointsreasoning effort: maxArtificial Analysis (opens in a new tab)independent · 2026-11-17
Artificial Analysis Intelligence Index5.0.1 / OpenAI GPT-6.2 launchIndex score · Higher is better57.3 pointscost per task usd: 1.01 · reasoning effort: maxOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
Artificial Analysis Intelligence Index5.0.1 / OpenAI GPT-6.2 launchIndex score · Higher is better55.7 pointscost per task usd: 0.65 · reasoning effort: xhighOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
Artificial Analysis Intelligence Index5.0.1 / OpenAI GPT-6.2 launchIndex score · Higher is better54.9 pointscost per task usd: 0.56 · reasoning effort: highOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
Artificial Analysis Intelligence Index5.0.1 / OpenAI GPT-6.2 launchIndex score · Higher is better52.7 pointscost per task usd: 0.41 · reasoning effort: mediumOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
Artificial Analysis Intelligence Index5.0.1 / OpenAI GPT-6.2 launchIndex score · Higher is better40.6 pointscost per task usd: 0.18 · reasoning effort: lowOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
Coronavirus–ACE2 Cell-Entry ScreenGPT-6.2 system cardMedian composite score · Higher is better0.441 scoreace2 proteins: 35 · coronaviruses: 3 · dataset: unpublished academic collaboratorOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
ExploitBench Internal PortJune–August 2026 / GPT-6.2 system cardArbitrary code execution rate · Higher is better50.5%aggregation: equal-weight mean · partial credit: false · targets: ["V8","Chrome"]OpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
ExploitBench V8GPT-6.2 system cardMean capability credit · Higher is better100%attempts per vulnerability: 5 · capability flags: 16OpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
FrontierCode2.0 / OpenAI GPT-6.2 launchAccuracy · Higher is better43.8%cost per task usd: 1.29 · reasoning effort: maxOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
FrontierCode2.0 / OpenAI GPT-6.2 launchAccuracy · Higher is better39.8%cost per task usd: 0.98 · reasoning effort: xhighOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
FrontierCode2.0 / OpenAI GPT-6.2 launchAccuracy · Higher is better39.7%cost per task usd: 0.88 · reasoning effort: highOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
FrontierCode2.0 / OpenAI GPT-6.2 launchAccuracy · Higher is better38.3%cost per task usd: 0.68 · reasoning effort: mediumOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
FrontierCode2.0 / OpenAI GPT-6.2 launchAccuracy · Higher is better33.1%cost per task usd: 0.4 · reasoning effort: lowOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
GDPval v2 (Internal)2 / OpenAI GPT-6.2 launchTask score · Higher is better46.9%output tokens: 33428 · reasoning effort: maxOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
GDPval v2 (Internal)2 / OpenAI GPT-6.2 launchTask score · Higher is better45%output tokens: 18790 · reasoning effort: xhighOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
GDPval v2 (Internal)2 / OpenAI GPT-6.2 launchTask score · Higher is better42.7%output tokens: 12420 · reasoning effort: highOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
GDPval v2 (Internal)2 / OpenAI GPT-6.2 launchTask score · Higher is better34.8%output tokens: 4722 · reasoning effort: mediumOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
GDPval v2 (Internal)2 / OpenAI GPT-6.2 launchTask score · Higher is better23.1%output tokens: 2006 · reasoning effort: lowOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
GPQA DiamondGPT-6.2 system card / no toolsAccuracy · Higher is better96%questions: 198 · No toolsOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
Internal Research DebuggingGPT-6.2 system cardMean rubric score · Higher is better74.66%missing scores: zero · stage: Initial StageOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
KernelGen 1PGPT-6.2 system cardMean rubric score · Higher is better74.71%missing scores: zero · stage: Initial StageOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
MLE-Bench RevisedGPT-6.2 system cardMean reference percentile · Higher is better91.38 percentilestage: Secondary StageOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
Multi-select Virology TroubleshootingGPT-6.2 system card / observed pass@1Pass@1 · Higher is better55.4%questions: 322 · score variant: observed · tools: text and image inputOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
NanoGPTGPT-6.2 system cardBaseline training time saved · Higher is better14.59%development time hours: 2 · gpu: 1× H100 · note: The system card states the two Astra models use slightly different evaluation versions. · stage: Secondary StageOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
Phage–Plasmid Co-evolutionGPT-6.2 system cardPair-weighted negative log-likelihood · Lower is better12.389 NLLaggregation: median · lower is better: trueOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
PostTrainBench LiteGPT-6.2 system cardPerformance gap closed · Higher is better44.89%stage: Secondary StageOpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
SEC-Bench ProMay 2026 / GPT-6.2 system cardVulnerability reproduction pass@1 · Higher is better88.34%engines: ["V8","SpiderMonkey"] · release: May 2026 · vulnerabilities: 183OpenAI ↗ (opens in a new tab)provider reported · 2026-11-17
SHP2 Protein Function PredictionGPT-6.2 system cardMean median R² · Higher is better0.396 R²assays: 3 · dataset: unpublished Velocity Bio · mutations: 411OpenAI ↗ (opens in a new tab)provider reported · 2026-11-17