Up to four models
Gemini 4 Carbon vs GPT-6.1 Sol
On the index (GPT-4 = 100), Gemini 4 Carbon scores 198 and GPT-6.1 Sol 191. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
198182–215
WeightsClosed
ReleasedOct 2026
Price in / out$2.0 / $10
Context1.05M
Core tests taken4 of 9
GPT-6.1 Sol
191175–207
WeightsClosed
ReleasedSep 2026
Price in / out$2.0 / $10
Context1.05M
Core tests taken6 of 9
Gemini 4 Carbon leads GPT-6.1 Sol by 7 points, ahead on 3 of 4 shared core tests, at a similar price.
Test by testthird-party results
Every result as a table
| Test | Gemini 4 Carbon | GPT-6.1 Sol |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 96.5% | 95.4% |
| EBR-bench | 87.6% | 54.3% |
| SimpleBench | 92.6% | 82.9% |
| SimpleQA Verified | 77.7% | 73.9% |
| Maths | ||
| FrontierMath (tiers 1-3) | 90.5% | 93.7% |
| AIME-style maths (OTIS mock) | 100.0% | 100.0% |
| Chess puzzles | 78.0% | 68.0% |
| FrontierMath (tier 4) | 95.1% | 100.0% |
| Coding | ||
| Terminal-Bench 4.0 | 63.1% | 55.0% |
| Vibe Code Bench v1.1 | 89.1% | 88.9% |
| Agents | ||
| APEX-Agents | 84.2% | 60.0% |
| Furniture assembly | 77.5% | 80.0% |
| Mystery game puzzles | 73.0% | 80.0% |
| Professional work | ||
| HLAB-Vals-1.1 | 17.5% | 6.3% |
| Legal Research Bench | 55.8% | 38.5% |
| Tax Agent Bench | 51.8% | 21.8% |
Tests at least two of these models have taken. Bold rows are the core tests.