Up to four models
GPT-6.2 Astra vs Claude Sonnet 5.5
On the index (GPT-4 = 100), GPT-6.2 Astra scores 202 and Claude Sonnet 5.5 187. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
GPT-6.2 Astra
202184–220
WeightsClosed
ReleasedNov 2026
Price in / out$8.0 / $40
Context1.05M
Core tests taken3 of 9
Claude Sonnet 5.5
187171–203
WeightsClosed
ReleasedSep 2026
Price in / out$2.0 / $10
Context1M
Core tests taken7 of 9
GPT-6.2 Astra leads Claude Sonnet 5.5 by 15 points, ahead on 2 of 3 shared core tests, at 4.0× the price.
Test by testthird-party results
GPT-6.2 AstraClaude Sonnet 5.5
Every result as a table
| Test | GPT-6.2 Astra | Claude Sonnet 5.5 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 96.8% | 95.6% |
| SimpleQA Verified | 78.5% | 46.5% |
| Maths | ||
| FrontierMath (tiers 1-3) | 92.6% | 88.8% |
| AIME-style maths (OTIS mock) | 100.0% | 100.0% |
| Chess puzzles | 78.0% | 59.0% |
| FrontierMath (tier 4) | 100.0% | 80.5% |
| Coding | ||
| Terminal-Bench 4.0 | 63.1% | 64.1% |
| Vibe Code Bench v1.1 | 89.9% | 92.4% |
| MirrorCode | 67.8% | 97.8% |
| Agents | ||
| BioMysteryBench | 80.7% | 81.1% |
| Terminal-Bench-Science | 71.4% | 47.1% |
| Furniture assembly | 89.2% | 75.0% |
| Mystery game puzzles | 95.0% | 65.0% |
| Professional work | ||
| HLAB-Vals-1.1 | 16.3% | 10.4% |
| Legal Research Bench | 42.8% | 48.1% |
| Tax Agent Bench | 21.8% | 42.0% |
| Novel problems | ||
| MysteryMechanism | 53.1% | 49.1% |
Tests at least two of these models have taken. Bold rows are the core tests.