Up to four models
GPT-6.2 Astra vs Kimi K3.1 Pro
On the index (GPT-4 = 100), GPT-6.2 Astra scores 202 and Kimi K3.1 Pro 179. 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
Kimi K3.1 Pro
179163–195
WeightsOpen
ReleasedOct 2026
Price in / out$0.24 / $8.4
Context1.05M
Core tests taken4 of 9
GPT-6.2 Astra leads Kimi K3.1 Pro by 23 points, ahead on 2 of 3 shared core tests, at 7.0× the price.
Test by testthird-party results
GPT-6.2 AstraKimi K3.1 Pro
Every result as a table
| Test | GPT-6.2 Astra | Kimi K3.1 Pro |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 96.8% | 94.2% |
| SimpleQA Verified | 78.5% | 62.2% |
| Maths | ||
| FrontierMath (tiers 1-3) | 92.6% | 78.3% |
| AIME-style maths (OTIS mock) | 100.0% | 100.0% |
| Chess puzzles | 78.0% | 45.0% |
| FrontierMath (tier 4) | 100.0% | 65.8% |
| Coding | ||
| Terminal-Bench 4.0 | 63.1% | 63.6% |
| Vibe Code Bench v1.1 | 89.9% | 84.9% |
| Agents | ||
| BioMysteryBench | 80.7% | 75.6% |
| Terminal-Bench-Science | 71.4% | 31.4% |
| Furniture assembly | 89.2% | 55.8% |
| Mystery game puzzles | 95.0% | 42.0% |
| Professional work | ||
| HLAB-Vals-1.1 | 16.3% | 11.7% |
| Legal Research Bench | 42.8% | 37.5% |
| Tax Agent Bench | 21.8% | 24.9% |
| Novel problems | ||
| MysteryMechanism | 53.1% | 26.1% |
Tests at least two of these models have taken. Bold rows are the core tests.