Up to four models
GPT-6.2 vs Gemini 4 Argon
On the index (GPT-4 = 100), GPT-6.2 scores 202 and Gemini 4 Argon 191. 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
202184–220
WeightsClosed
ReleasedNov 2026
Price in / out$8.0 / $40
Context1.05M
Core tests taken3 of 9
191176–207
WeightsClosed
ReleasedSep 2026
Price in / out$2.0 / $10
Context1.05M
Core tests taken6 of 9
GPT-6.2 leads Gemini 4 Argon by 11 points, ahead on 3 of 3 shared core tests, at 4.0× the price.
Test by testthird-party results
GPT-6.2
Gemini 4 Argon
Every result as a table
| Test | GPT-6.2 | Gemini 4 Argon |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 96.8% | 96.4% |
| EBR-bench | 92.4% | 64.8% |
| SimpleQA Verified | 78.5% | 76.0% |
| Maths | ||
| FrontierMath (tiers 1-3) | 92.6% | 86.0% |
| AIME-style maths (OTIS mock) | 100.0% | 100.0% |
| Chess puzzles | 78.0% | 59.0% |
| FrontierMath (tier 4) | 100.0% | 78.0% |
| Coding | ||
| Terminal-Bench 4.0 | 63.1% | 57.6% |
| Vibe Code Bench v1.1 | 89.9% | 91.9% |
| MirrorCode | 67.8% | 58.9% |
| Agents | ||
| BioMysteryBench | 80.7% | 76.3% |
| Terminal-Bench-Science | 71.4% | 44.3% |
| Furniture assembly | 89.2% | 72.5% |
| Mystery game puzzles | 95.0% | 64.0% |
| Professional work | ||
| HLAB-Vals-1.1 | 16.3% | 27.1% |
| Legal Research Bench | 42.8% | 54.8% |
| Tax Agent Bench | 21.8% | 49.2% |
| Novel problems | ||
| MysteryMechanism | 53.1% | 45.5% |
Tests at least two of these models have taken. Bold rows are the core tests.