specs at a glance

Leaderboard rank#1 of 13
SWE-bench Verified96.2%
SWE-bench Pro
Terminal-Bench88.8%
Input price / 1M$5
Output price / 1M$30
Context window
Open weightsNo
AccessAPI · Codex (public since Jul 9 2026)
MakerOpenAI

how good is GPT-5.6 Sol at coding?

GPT-5.6 Sol holds the #1 spot on our leaderboard with 96.2% on SWE-bench Verified — the highest confirmed score of any model we track. Terminal-Bench (agentic terminal work): 88.8%.

Score provenance: Independent (vals.ai, Jul 14 2026, mini-swe-agent bash-only harness): SWE-bench Verified 96.20% ±0.86 — the top score on the board. Verified Jul 17, 2026; it had been unranked since Jun 26 because OpenAI published no SWE-bench number of its own, and it still has not. Read the #1 with care: the 1.2-point lead over Claude Fable 5 (95.00% ±0.98) is inside the combined margin of error (~0.9 sigma, not significant), so the two are a statistical tie and we rank Sol first only because it scored higher. Where it does separate is task length — 98% on 1-4 hour tasks vs 93% for Fable 5. OpenAI's own Terminal-Bench 2.1 claim is 88.8% (Sol) / 91.9% (Sol Ultra). No SWE-bench Pro score published. Pricing $5/$30 per 1M.

what does GPT-5.6 Sol cost?

$5 per 1M input tokens and $30 per 1M output — #10 cheapest of the 13 models we track. Coding workloads are output-heavy, so weight the output rate when budgeting. Run your own volume through the AI API cost calculator for a monthly estimate.

where can you use it?

Available via API · Codex (public since Jul 9 2026). As a proprietary model, you're on the maker's infrastructure and release schedule.

head-to-head

Full storyOpenAI puts GPT-5.6 Sol on Cerebras wafer-scale silicon

Ranked on our AI Coding Leaderboard — scores confirmed against primary sources only, updated 2026-07-17.