Automated page. Written and translated automatically by AI and checked against the sources by software; no human editor. SI-IQ is an index built from public benchmark results, not an IQ test. How it works
Claude Opus 5.5 vs Gemini 4 Argon: which is smarter?
Claude Opus 5.5 has an SI-IQ of 144 and Gemini 4 Argon has 140. The table compares them area by area using only independent benchmark results.
| Metric | Claude Opus 5.5 | Gemini 4 Argon |
|---|---|---|
| SI-IQ | 144141–148 | 140137–143 |
| Reasoning | 146 | 142 |
| Math | 145 | 138 |
| Knowledge | 137 | 148 |
| Developer | Anthropic | Google DeepMind |
| Released | Sep 22, 2026 | Sep 30, 2026 |
| Access | API access | Not stated |
| Price in / out (USD per 1M tokens) | $4.00 / $20 | $2.00 / $10 |
| Benchmarks used | 8 | 8 |
Benchmarks every compared model was tested on
Raw scores as published by the evaluators.
| Benchmark | Claude Opus 5.5 | Gemini 4 Argon |
|---|---|---|
| Chess Puzzles | 67.0% | 59.0% |
| FrontierMath Tier 4 | 95.0% | 78.0% |
| FrontierMath Tiers 1–3 | 91.2% | 86.0% |
| Furniture Assembly | 83.3% | 72.5% |
| GPQA Diamond | 90.6% | 96.4% |
| GPQA Diamond (OpenRouter run) | 90.2% | 96.5% |
| Mystery Game Puzzles | 71.0% | 64.0% |
| OTIS Mock AIME 2024–2025 | 100.0% | 100.0% |
| SimpleQA Verified | 72.2% | 76.0% |
| τ²-bench Airline (OpenRouter run) | 75.6% | 78.7% |
The difference of 4 points is within the statistical uncertainty: the two models are roughly on par.
Data sources: Arena leaderboard dataset on Hugging Face (CC BY 4.0); Epoch AI, ‘Capabilities & benchmarking’ (CC BY 4.0); API list prices via LiteLLM's price table (MIT); each price links to the developer's pricing page; Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter..