GPT-5.6 Sol

ModelActive

by OpenAI · family “gpt-sol”

GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks... (description from the OpenRouter listing)

in: filein: imagein: textout: textReasoningTool useStructured output

Epoch Capabilities Index

162.0 #6 of 268

90% CI 159.6 – 165.9

Listing ↗

Released

9 Jul 2026

Context window

1.05M tokens

Max output

128K tokens

Input $ / 1M tokens

$2.00

Output $ / 1M tokens

$10.0

Cached input $ / 1M

$0.20

Each benchmark shown separately with its own source

Benchmark results (20)

All benchmarks

Benchmark	Domain	Score	vs best recorded	Setting	Run	Source
Furniture Assembly	multimodal	56.7% ±6.3	68%	max	10 Sep 2026	Epoch ↗
LMCA	agents	58.4%	89%	max	—	External ↗
DTBench	reasoning	95.5%	97%	max	—	External ↗
Mystery Game Puzzles	games	58.0% ±5.0	69%	max	28 Jul 2026	Epoch ↗
EBR-bench	reasoning	44.8% ±4.2	59%	max	4 Sep 2026	Epoch ↗
MirrorCode	coding	20.0% ±9.2	27%	high	10 Aug 2026	Epoch ↗
OSWorld 2.0	agents	27.3%	87%	max	—	External ↗
FrontierMath-Tiers-1-3-v2-Private	math	89.1% ±1.8	95%	max	9 Jul 2026	Eval log ↗
FrontierMath-Tier-4-v2-Private	math	82.9% ±5.9	85%	max	9 Jul 2026	Eval log ↗
DeepSWE	coding	72.7%	98%	max	—	External ↗
PostTrainBench	agents	36.2%	87%	max	—	External ↗
ProofBench	math	83.0%	83%	max	—	External ↗
Chess Puzzles	games	55.0% ±5.0	76%	max	9 Jul 2026	Epoch ↗
SimpleQA Verified	knowledge	69.7% ±1.5	92%	max	10 Aug 2026	Epoch ↗
ARC-AGI-2	reasoning	92.5%	97%	max	—	External ↗
WeirdML	coding	88.8% ±0.0	95%	high	—	External ↗
OTIS Mock AIME 2024-2025	math	100.0%	100%	max	9 Jul 2026	Epoch ↗
Balrog	games	60.0%	88%	max	—	External ↗
GPQA diamond	science	93.5% ±1.6	98%	max	9 Jul 2026	Epoch ↗
ARC-AGI	reasoning	97.0%	98%	high	—	External ↗

Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.

API list price over time

Price history

$ per 1M tokens

4 observations (OpenRouter listing + Internet Archive snapshots). History accumulates with every ingest run; a single point means no change has been observed yet.