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

How smart is Claude Opus 4.6?

123 SI-IQ · 90% interval 120–126
Rank 34 of 80 ranked models · Plausible rank range 20–46

Claude Opus 4.6 is a model from Anthropic, released on Feb 5, 2026. Its SI-IQ is 123 (90% interval 120–126), estimated from 9 benchmark results by 2 independent evaluators. Its strongest area is Math and its weakest is Reasoning.

Facts

Developer
Anthropic
Released
Feb 5, 2026
Access
API access
Benchmarks used
9 results from 2 evaluators
API price
$5.00 input / $25 output per 1M tokens (developer's price list, Oct 18, 2026)
Context window
1,000,000 tokens

Ability by area (SI-IQ, 90% interval)

6080100120140160Reasoning117Math125Knowledge124

Every benchmark result we used

Each score is one value exactly as the source published it: for Epoch AI the best of its run settings, for OpenRouter the median hosting provider (the developer's own hosting when it ran the test). “Implied SI-IQ” is the ability that this single result points to; the overall SI-IQ is their precision-weighted average.

Benchmark Area Score Implied SI-IQ Evaluated by As listed by the source Retrieved Source
Chess Puzzles Reasoning 21.0% 113 Epoch AI claude-opus-4-6_max Oct 18, 2026 Epoch AI Benchmarking Hub · data file
Furniture Assembly not in index Reasoning 28.3% — Epoch AI claude-opus-4-6_max Oct 18, 2026 Epoch AI Benchmarking Hub · data file
Mystery Game Puzzles Reasoning 25.0% 119 Epoch AI claude-opus-4-6_max Oct 18, 2026 Epoch AI Benchmarking Hub · data file
FrontierMath Tier 4 Math 26.8% 124 Epoch AI claude-opus-4-6_max Oct 18, 2026 Epoch AI Benchmarking Hub · data file
FrontierMath Tiers 1–3 Math 66.0% 126 Epoch AI claude-opus-4-6_max Oct 18, 2026 Epoch AI Benchmarking Hub · data file
OTIS Mock AIME 2024–2025 Math 94.4% 122 Epoch AI claude-opus-4-6_64K Oct 18, 2026 Epoch AI Benchmarking Hub · data file
SWE-bench Verified (Epoch AI run) Coding 78.7% 128 Epoch AI claude-opus-4-6 Oct 18, 2026 Epoch AI Benchmarking Hub · data file
GPQA Diamond Knowledge 90.5% 125 Epoch AI claude-opus-4-6_32K Oct 18, 2026 Epoch AI Benchmarking Hub · data file
GPQA Diamond (OpenRouter run) Knowledge 85.7% 120 OpenRouter anthropic/claude-4.6-opus-20260205
Anthropic · first-party provider (1 of 5 rows)		 Oct 18, 2026 OpenRouter benchmark datasets · data file
SimpleQA Verified Knowledge 47.0% 126 Epoch AI claude-opus-4-6_max Oct 18, 2026 Epoch AI Benchmarking Hub · data file
τ²-bench Airline (OpenRouter run) Agents 76.4% 132 OpenRouter anthropic/claude-4.6-opus-20260205
Anthropic · first-party provider (1 of 5 rows)		 Oct 18, 2026 OpenRouter benchmark datasets · data file

Human preference (Arena)

On the Arena leaderboard, where people vote between two anonymous answers, Claude Opus 4.6 has a rating of 1,503 (1,500–1,506) from 81,394 votes (published Oct 15, 2026). Human preference is a different measure from benchmark ability and is not part of SI-IQ. Arena (Hugging Face)

Models with similar SI-IQ

ModelSI-IQ
Gemini 3 FlashGoogle DeepMind122Claude Opus 4.6 vs Gemini 3 Flash
DeepSeek V4 Flash 0731DeepSeek124Claude Opus 4.6 vs DeepSeek V4 Flash 0731
Gemini 3.6 FlashGoogle DeepMind125Claude Opus 4.6 vs Gemini 3.6 Flash
Kimi K2.6Moonshot121Claude Opus 4.6 vs Kimi K2.6
Qwen3.7-MaxAlibaba125Claude Opus 4.6 vs Qwen3.7-Max

Computed with SI-IQ method version 1.0.0. Read the full methodology

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..