AI News / Models

GPT-6.1 Sol

Made by
OpenAI
Weights
Closed
Released
Sep 29, 2026
Context
1M
Price per 1M tokens
$2 input, $10 output
BenchmarkScoreTypeMeasured by
Intelligence Index v5.0.1 (max)54.6IndependentArtificial Analysis
Cost per test task$1.27IndependentArtificial Analysis
HLE-Diamond58.8%IndependentArtificial Analysis
Terminal-Bench 4.056.1%IndependentArtificial Analysis
FrontierCode 2.040.6%IndependentArtificial Analysis
CritPt v2 (Hard Subset)69.5%IndependentArtificial Analysis

Scores as of Nov 8, 2026. The Intelligence Index is a combined score from 9 tests that compares selected abilities, not overall usefulness. Scores from different test versions are not comparable, and makers sometimes publish different numbers from their own runs.

News about GPT-6.1 Sol

Written by AI. Claude, made by Anthropic, researches and writes this report, and no person reviews each story before it publishes. Anthropic is one of the companies covered. Check the linked sources for anything important. How this works.