GPT-6.2 Sol

  • New
  • Closed weights
  • Reasoning
  • Input: file · image · text
  • Released 2026-11
RankedEnough results for an index.
IndexAll categories, out of 100.76.0±4.6Median 50.7
CoverageIndex weight that has results.85%
SpeedOutput tokens per second.56/sMedian 76/s
First tokenSeconds to the first output token.2.0 sMedian 1.1 s
Input / 1MUS dollars per 1M input tokens.$2.00batch $1.00Median $0.60
Output / 1MUS dollars per 1M output tokens.$10.00batch $5.00 Batch price per 1M output tokens.Median $2.50
ContextMaximum tokens in one request.1.05MMedian 262K
EloLMArena rating and rank.1414±12 #140Median 1425

Details

From OpenRouter
API IDThe model ID on OpenRouter.
openai/gpt-6.2-sol
Max outputMaximum output tokens per request.
128K
Knowledge cutoffLast date of training data.
—
ToolsTool calls on OpenRouter.
Yes
JSON outputOutput follows a given JSON schema.
Yes
Cache read / 1MUS dollars per 1M cached tokens.
$0.10
Weights
—
RetiresDate OpenRouter removes the model.
—

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.14 counted72.915 / 221
CodingCode writing and repair.3 counted78.67 / 214
ReasoningLogic problems and puzzles.4 counted78.810 / 225
MultimodalTasks with images and text.1 counted73.2—
KnowledgeFacts and expert knowledge.4 counted75.79 / 266
MultilingualTasks in many languages.1 counted71.9—
InstructionTasks with strict prompt rules.None counted——
MathMath problems.None counted——

Results

27 counted
BenchmarkResultThe score from the source.PlacePlace among results on this benchmark.
Graduate-Level Google-Proof Q&AKnowledge96.0%2 / 144
EuroEval SpanishMultilingual69.0% ±0.43 / 194
EuroEval SwedishMultilingual77.1% ±0.44 / 213
EuroEval DutchMultilingual73.4% ±0.44 / 192
EuroEval ItalianMultilingual77.4% ±0.34 / 191
EuroEval PolishMultilingual66.2% ±0.45 / 227
GPQA Diamond · BenchLMKnowledge96.0%2 / 87
EuroEval GermanMultilingual66.8% ±0.55 / 208
EuroEval PortugueseMultilingual74.0% ±0.45 / 199
EuroEval FrenchMultilingual75.7% ±0.45 / 195
ARC-AGI-1 (semi-private)Reasoning97.5%7 / 132
Terminal-Bench 4.0Agentic60.6%7 / 68
ARC-AGI-2 (semi-private)Reasoning85.8%15 / 137
Vibe Code Bench v1.1Coding87.6% ±2.216 / 130
Terminal-Bench 4.1.0Agentic61.5% ±1.47 / 52
HealthBench ProfessionalKnowledge65.9%3 / 21
ARC-AGI-3 (semi-private)Reasoning54.9%5 / 30
Bug Hunt BenchCoding54.7%5 / 30
Agent Arena steerabilityAgentic13.410 / 59
Artificial Analysis GDP.pdfAgentic30.0%4 / 23
FrontierCode 2.0Coding43.8%6 / 32
Agent Arena task outcomeAgentic10.912 / 59
Terminal-Bench-Science 0.1Agentic68.0%4 / 15
CWE-bench v2Agentic66.0%8 / 20
Terminal-Bench-ScienceScience58.6% ±5.94 / 48
ARC-AGI-1 (public eval)Reasoning98.1%12 / 116
ARC-AGI-2 (public eval)Reasoning91.7%15 / 127
BioMysteryBenchScience77.8% ±0.69 / 34
MysteryMechanismScience36.9% ±3.211 / 34
HLAB-Vals-1.1Legal12.1% ±2.721 / 42
Legal Research BenchLegal37.0% ±3.452 / 98
Tax Agent BenchFinance24.8% ±3.149 / 89
Harvey LAB-AA v1.1Agentic11.1%—

Sources

BenchLMCC BY-NC 4.0OpenRouterTerms restrict reuseARC Prize FoundationTerms restrict reuseVals AINo licence statedEuroEvalMITTerminal-BenchNo licence statedLMArenaCC BY 4.0models.devMITCheaper InferenceNo licence stated

History

13 releases
Index74.9 → 76.0
18 Nov 202621 Nov 2026
Output / 1M$10.00 → $10.00
18 Nov 202621 Nov 2026

Questions

How much does GPT-6.2 Sol cost?
$2.00 per 1M input tokens, $10.00 per 1M output tokens.
How good is GPT-6.2 Sol?
Its index is 76.0 out of 100. That is place 10 of 282 ranked models.
What is GPT-6.2 Sol best at?
Coding: 78.6 out of 100, place 7 of 214.
How fast is GPT-6.2 Sol?
56 output tokens per second, 2.0 s to the first token.
What is the context window of GPT-6.2 Sol?
1.05M tokens.
Is GPT-6.2 Sol open source?
No. Its weights are not published.
When was GPT-6.2 Sol released?
November 2026.

Badge

GPT-6.2 Sol on Inference360: place 10 of 282, index 76.0

Compare with

GPT-6.1 Sol76.2Gemini 4 Hydrogen76.2Muse Wonder Full75.8Claude Sonnet 5.575.7GPT-6 Astra76.5

Lower price

GPT-6.1 Terra75.1 · $5.00/1MGemini 4 Hydrogen76.2 · $7.50/1M

More from OpenAI

All models
GPT-6.2 Astra79.5GPT-6.2 Sol ProUnrankedGPT-6.2 Astra ProUnrankedGPT-Live-1.1UnrankedGPT-6 CyberUnranked