Up to four models
Gemini 4 Carbon vs Claude Opus 5.5
On the index (GPT-4 = 100), Gemini 4 Carbon scores 198 and Claude Opus 5.5 195. 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
Claude Opus 5.5
195178–211
WeightsClosed
ReleasedSep 2026
Price in / out$4.0 / $20
Context1M
Core tests taken6 of 9
Gemini 4 Carbon and Claude Opus 5.5 are too close to call (4 points apart, within the uncertainty), ahead on 2 of 4 shared core tests, and costs 2.0× less.
Test by testthird-party results
Every result as a table
| Test | Gemini 4 Carbon | Claude Opus 5.5 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 96.5% | 94.1% |
| EBR-bench | 87.6% | 71.4% |
| SimpleBench | 92.6% | 88.4% |
| SimpleQA Verified | 77.7% | 72.2% |
| Maths | ||
| FrontierMath (tiers 1-3) | 90.5% | 91.2% |
| AIME-style maths (OTIS mock) | 100.0% | 100.0% |
| Chess puzzles | 78.0% | 67.0% |
| FrontierMath (tier 4) | 95.1% | 95.0% |
| Coding | ||
| Terminal-Bench 4.0 | 63.1% | 65.1% |
| Vibe Code Bench v1.1 | 89.1% | 90.3% |
| FrontierSWE | 61.2% | 62.3% |
| Agents | ||
| APEX-Agents | 84.2% | 73.5% |
| Furniture assembly | 77.5% | 83.3% |
| Mystery game puzzles | 73.0% | 71.0% |
| Professional work | ||
| HLAB-Vals-1.1 | 17.5% | 9.2% |
| Legal Research Bench | 55.8% | 50.5% |
| Tax Agent Bench | 51.8% | 44.5% |
Tests at least two of these models have taken. Bold rows are the core tests.