Atlas

Models

← All models

GPT-6.1 Sol

OpenAI · 2026-09-29

GPT-6.1 Sol is OpenAI's September 29, 2026 reasoning model for coding, computer use, and professional work. It accepts text and image inputs and produces text, with low, medium, high, xhigh, and max reasoning effort. Tool calling uses the Responses API. Its documented total context window is 1,050,000 tokens, with at most 922,000 input tokens and 128,000 output tokens.

Benchmark scores

BenchmarkScore
AA-Briefcase v1.1 Elo1564
AA-LCR v1.184.0
AA-Omniscience Index41.5
APEX-Agents 1.173.2
APEX-Agents 1.1 Pass@160.0
APEX-SWE46.9
ARC-AGI-198.5
ARC-AGI-294.2
ARC-AGI-3 (Semi-Private)96.4
Arena Code WebDev — Brand & Marketing1677
Arena Code WebDev — Consumer Product1738
Arena Code WebDev — Data & Analytics1632
Arena Code WebDev — Gaming1853
Arena Code WebDev — HTML1809
Arena Code WebDev — React1762
Arena Code WebDev — Reference-Based Design1793
Arena Code WebDev — Simulations1846
Artificial Analysis Intelligence Index v4.3.251.8
Artificial Analysis Omniscience Accuracy62.1
Artificial Analysis Omniscience Hallucination Rate49.4
ArXivMath 05/202695.0
ArXivMath 06/202694.4
ArXivMath 08/2026 (Native Harnesses)96.5
AutomationBench-AA 1.0.666.6
BioMysteryBench — Hard (Vals)39.2
BioMysteryBench — Human-solvable (Vals)89.0
BioMysteryBench (Vals Terminus 2)79.6
BrokenArXiv 05/202690.0
BrokenArXiv 06/2026100.0
BrokenArXiv 08/2026 (Native Harnesses)86.3
Loading Atlas data…