IQ of SI
English ▾

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 Sonnet 5.5 vs GPT-5.6 Sol: which is smarter?

Claude Sonnet 5.5 has an SI-IQ of 140 and GPT-5.6 Sol has 140. The table compares them area by area using only independent benchmark results.

Data as of Oct 18, 2026 · method 1.0.0

MetricClaude Sonnet 5.5GPT-5.6 Sol
SI-IQ140137–143140137–143
Reasoning142140
Math140141
Knowledge137139
DeveloperAnthropicOpenAI
ReleasedSep 28, 2026Jul 9, 2026
AccessAPI accessAPI access
Price in / out (USD per 1M tokens)$2.00 / $10$4.00 / $20
Benchmarks used99
Claude Sonnet 5.5GPT-5.6 Sol
130140150SI-IQReasoningMathKnowledge

Benchmarks every compared model was tested on

Raw scores as published by the evaluators.

BenchmarkClaude Sonnet 5.5GPT-5.6 Sol
Chess Puzzles59.0%59.0%
FrontierMath Tier 480.5%82.9%
FrontierMath Tiers 1–388.8%89.1%
Furniture Assembly not in index75.0%56.7%
GPQA Diamond95.6%93.5%
GPQA Diamond (OpenRouter run)92.9%92.3%
Mystery Game Puzzles65.0%58.0%
OTIS Mock AIME 2024–2025100.0%100.0%
SimpleQA Verified46.5%69.7%
τ²-bench Airline (OpenRouter run)77.5%73.3%

The difference of 0 points is within the statistical uncertainty: the two models are roughly on par.

Data sources: Epoch AI, ‘Capabilities & benchmarking’ (CC BY 4.0); LiteLLM, model_prices_and_context_window.json (MIT); Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter (licences and changes).