GPT-6.2 Astra hits #2 on Intelligence Index at 20% lower price, coding flat
ArtificialAnlys · x · 2026-11-18
Artificial Analysis reviewed OpenAI's GPT-6.2 Astra and Sol:
- Pricing: Astra drops to $8/$40 (20% below GPT-6 Astra), cached input cut from $1.00 to $0.40/M tokens; Sol unchanged at $2/$10.
- Intelligence Index: Astra jumps 5 points, overtaking Gemini 4 Carbon (60) and Claude Opus 5.5 (59), trailing only Anthropic's Claude Fable 5.2; Sol gains 2 points to 57, matching GPT-6 Astra at 15% of the cost.
- Efficiency: OpenAI models now occupy most of the Cost-per-Task and Output-Token Pareto frontiers.
- Strengths: Leads Terminal-Bench-Science and AA-3D (1318); tops AA-Robotics v0.1 (79/78 vs Claude Fable 5.2's 75).
- Weakness: Coding Agent Index flat for Astra, down 3 for Sol, driven by a 14-point SWE-Atlas-QnA-AA drop from omitting key facts.
Related event: GPT-6.2 Cuts Price 20% but Coding Stalls in Third-Party Benchmarks(4 posts)→
More from Models
- GPT-6.2 Astra hits near-parity with Fable 5.2 at far lower cost, reigniting frontier race debate — daniel_mac8 · 2026-11-18
- GPT-6.2 Astra scores 100% on ARC-AGI-3, first model to max the benchmark — patience_cave · 2026-11-18
- GPT-6.2 fails to beat GPT-6 on Coding Agent Index, trailing Claude and Gemini — realsohamparekh · 2026-11-18
- Teknium flags inconsistent OpenAI demos: was GPT-6 quietly nerfed before GPT-6.2? — Teknium · 2026-11-18
- GPT-6.2 Astra beats Opus 5.5 across agent benchmarks at 3-6x lower cost — VraserX · 2026-11-18
- Side-by-side: GPT-6.2 Astra builds noticeably richer scenes than GPT-6 Astra — Angaisb_ · 2026-11-18