Skip to content
ModelCap

Launch report

GPT-6 Sol launch report

ModelCap · generated from recorded data

OpenAI's GPT-6 Sol was first listed on 22 September 2026. It entered the ModelCap Index at #3 of 276 ranked language models on 26 September 2026, 4 days after its listed release date, backed by 2 admitted benchmarks: Artificial Analysis Intelligence Index and LMArena Agent. Its first measurement, on 22 September 2026 on one benchmark, Artificial Analysis Intelligence Index, had placed it at #2 of 260; ModelCap counts a model as entered once two benchmarks back its position. As of 19 November 2026 it has been superseded by GPT-6.2 Sol and is #71 across all versions.

Position at entry · 26 September 2026
#3 of 276
Listing to first measurement
Same day
Position now · 19 November 2026
#71 all versions

Position at entry

Entry is the first board position backed by at least two admitted benchmarks. Read from the board's last published snapshot of each day named below; these values are fixed and do not change with later refreshes.

Listed release date
22 September 2026
First measurement · 22 September 2026
#2 of 260 ranked language modelsBacked by Artificial Analysis Intelligence Index
Entry · 26 September 2026
#3 of 276 ranked language modelsBacked by Artificial Analysis Intelligence Index, LMArena Agent
Neighbours at entry
Directly above: Claude Fable 5.1Directly below: MiMo-V2.6-Pro

Benchmark results

Published results admitted to the Index, as of 19 November 2026. Each board links to ModelCap's page for it and each result to its source.

Current public benchmark results for GPT-6 Sol
BenchmarkResultBoard positionPublished
Arena Overallgeneral · Max14581452–1463#68 of 42218 November 2026
Arena Codingcoding · Max15201511–1529#38 of 41718 November 2026
LMArena Agentagent · Max6.5%4.9%–8.0%#19 of 6818 November 2026
ARC-AGI-2 Verifiedreasoning · Max89.6%#27 of 29918 November 2026
ARC-AGI-3 Verifiedreasoning · Max4.6%#82 of 15118 November 2026

Against GPT-5.6 Sol

GPT-5.6 Sol is the previous release in the same family. Current results for both, as of 19 November 2026.

ModelCap Index
GPT-6 Sol: #71 across all versions · score 72.6GPT-5.6 Sol: #23 across all versions · score 79.4
Benchmarks with a published result for both GPT-6 Sol and GPT-5.6 Sol
BenchmarkGPT-6 SolGPT-5.6 SolDifference
Arena Overall1458Max1485X-High−27 Elo
Arena Coding1520Max1533X-High−13 Elo
LMArena Agent6.5%Max3.7%X-High+2.8 pts
ARC-AGI-2 Verified89.6%Max92.5%Max−2.9 pts
ARC-AGI-3 Verified4.6%Max7.8%Max−3.2 pts

Where the tested setting differs between the two rows, the difference compares the published results as they stand, not the same setting.

How this report is produced

ModelCap publishes a launch report when a newly released model first holds a measured position backed by at least two public benchmarks. The report is assembled automatically from ModelCap's own records: the board as it stood at entry, the results currently admitted to the Index and, where one exists, the estimate recorded before measurement. No text is written by hand, and no claim is made that the records do not contain. ModelCap does not run the benchmarks itself; each result links to the organisation that published it.

More launch reports