MODEL PROFILE / EDITION 2026.09
GPT-5.6 Sol
Teams standardised on Codex who want frontier agentic coding without Astra pricing
Balanced model evidence score; rank 13. No rank delta is shown because there is no prior numeric snapshot.
Best for
Teams standardised on Codex who want frontier agentic coding without Astra pricing
Price & access
$4 in / $20 out per 1M (promotional, was $5/$30); cached input $0.40; standard rates apply below 272K context
Evidence summary
First-party model card and pricing, a high-vote Arena row (+/-8) and third-party SWE-bench Pro placement all agree on tier.
Edition status
No prior snapshot. Tracked in the September 2026 baseline.
Strengths
- Highest-vote frontier Arena row in the OpenAI family (8,727 votes, +/-8)
- Terminal Bench 2.1 88.8% is the best number in Z.ai's cross-vendor table
- Solid agentic evidence: Agents' Last Exam 53.6%, OSWorld 2.0 65.7%
- Discounted while the promotion lasts ($4/$20)
Tradeoffs
- Terminal-Bench 4.0 37.3% is far behind GPT-6 Astra's 57.9%
- High TTFT (107 s at max effort)
- Frontend score is Codex-harness-assisted, so model-only quality is unclear
- Promotional price expires after Nov 21, 2026
Score profile
visual 76 · code 85 · agentic 84 · debug 78 · context 86 · speed 60 · value 66
Linked evidence
Evidence source 1 ↗Evidence source 2 ↗Evidence source 3 ↗Evidence source 4 ↗Evidence source 5 ↗Evidence source 6 ↗Compare this model on the full scoreboard
Open comparison view →Use the same published data, filters, and side-by-side metrics.