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 4.7?

127 SI-IQ · 90% interval 124–130
Rank 24 of 80 ranked models · Plausible rank range 13–38

Claude Opus 4.7 is a model from Anthropic, released on Apr 16, 2026. Its SI-IQ is 127 (90% interval 124–130), estimated from 9 benchmark results by 2 independent evaluators. Its strongest area is Knowledge and its weakest is Reasoning.

Facts

Developer
Anthropic
Released
Apr 16, 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)

6080100120140160Reasoning125Math127Knowledge127

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 41.0% 128 Epoch AI claude-opus-4-7_max Oct 18, 2026 Epoch AI Benchmarking Hub · data file
Furniture Assembly not in index Reasoning 33.3% — Epoch AI claude-opus-4-7_max Oct 18, 2026 Epoch AI Benchmarking Hub · data file
Mystery Game Puzzles Reasoning 28.0% 122 Epoch AI claude-opus-4-7_max Oct 18, 2026 Epoch AI Benchmarking Hub · data file
FrontierMath Tier 4 Math 31.7% 126 Epoch AI claude-opus-4-7_max Oct 18, 2026 Epoch AI Benchmarking Hub · data file
FrontierMath Tiers 1–3 Math 70.2% 128 Epoch AI claude-opus-4-7_max Oct 18, 2026 Epoch AI Benchmarking Hub · data file
OTIS Mock AIME 2024–2025 Math 97.8% 130 Epoch AI claude-opus-4-7_xhigh Oct 18, 2026 Epoch AI Benchmarking Hub · data file
SWE-bench Verified (Epoch AI run) Coding 83.5% 138 Epoch AI claude-opus-4-7_max Oct 18, 2026 Epoch AI Benchmarking Hub · data file
GPQA Diamond Knowledge 90.2% 124 Epoch AI claude-opus-4-7_xhigh Oct 18, 2026 Epoch AI Benchmarking Hub · data file
GPQA Diamond (OpenRouter run) Knowledge 89.2% 128 OpenRouter anthropic/claude-4.7-opus-20260416
Anthropic · first-party provider (1 of 5 rows)		 Oct 18, 2026 OpenRouter benchmark datasets · data file
SimpleQA Verified Knowledge 51.7% 131 Epoch AI claude-opus-4-7_xhigh Oct 18, 2026 Epoch AI Benchmarking Hub · data file
τ²-bench Airline (OpenRouter run) Agents 77.6% 134 OpenRouter anthropic/claude-4.7-opus-20260416
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 4.7 has a rating of 1,501 (1,497–1,505) from 65,116 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 3.1 ProGoogle DeepMind127Claude Opus 4.7 vs Gemini 3.1 Pro
Kimi K3Moonshot127Claude Opus 4.7 vs Kimi K3
Muse Spark OpenMeta AI127Claude Opus 4.7 vs Muse Spark Open
Gemini 3.5 FlashGoogle DeepMind126Claude Opus 4.7 vs Gemini 3.5 Flash
DeepSeek V4 Pro 0813DeepSeek128Claude Opus 4.7 vs DeepSeek V4 Pro 0813

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..