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 4.5?

115 SI-IQ · 90% interval 111–118
Rank 52 of 80 ranked models · Plausible rank range 38–64

Claude Opus 4.5 is a model from Anthropic, released on Nov 24, 2025. Its SI-IQ is 115 (90% interval 111–118), estimated from 10 benchmark results by 3 independent evaluators. Its strongest area is Agents and its weakest is Reasoning.

Facts

Developer
Anthropic
Released
Nov 24, 2025
Access
API access
Benchmarks used
10 results from 3 evaluators

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

6080100120140160Reasoning111Math113Knowledge118Agents127

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 14.0% 104 Epoch AI claude-opus-4-5-20251101_59K Oct 18, 2026 Epoch AI Benchmarking Hub · data file
Furniture Assembly not in index Reasoning 28.3% — Epoch AI claude-opus-4-5-20251101_64K Oct 18, 2026 Epoch AI Benchmarking Hub · data file
Mystery Game Puzzles Reasoning 22.0% 116 Epoch AI claude-opus-4-5-20251101_48K Oct 18, 2026 Epoch AI Benchmarking Hub · data file
FrontierMath Tier 4 Math 4.9% 113 Epoch AI claude-opus-4-5-20251101_32K Oct 18, 2026 Epoch AI Benchmarking Hub · data file
FrontierMath Tiers 1–3 Math 34.4% 113 Epoch AI claude-opus-4-5-20251101_32K Oct 18, 2026 Epoch AI Benchmarking Hub · data file
OTIS Mock AIME 2024–2025 Math 86.1% 112 Epoch AI claude-opus-4-5-20251101_32K Oct 18, 2026 Epoch AI Benchmarking Hub · data file
SWE-bench Verified (Epoch AI run) Coding 76.7% 124 Epoch AI claude-opus-4-5-20251101 Oct 18, 2026 Epoch AI Benchmarking Hub · data file
GPQA Diamond Knowledge 86.0% 116 Epoch AI claude-opus-4-5-20251101_32K Oct 18, 2026 Epoch AI Benchmarking Hub · data file
GPQA Diamond (OpenRouter run) Knowledge 86.1% 121 OpenRouter anthropic/claude-4.5-opus-20251124
Anthropic · first-party provider (1 of 5 rows)		 Oct 18, 2026 OpenRouter benchmark datasets · data file
SimpleQA Verified Knowledge 45.7% 125 Epoch AI claude-opus-4-5-20251101_32K Oct 18, 2026 Epoch AI Benchmarking Hub · data file
Berkeley Function Calling Leaderboard Agents 77.5% 137 UC Berkeley (Gorilla) Claude-Opus-4-5-20251101 (FC) Oct 18, 2026 Berkeley Function Calling Leaderboard · data file
τ²-bench Airline (OpenRouter run) Agents 77.0% 133 OpenRouter anthropic/claude-4.5-opus-20251124
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 4.5 has a rating of 1,470 (1,466–1,473) from 72,899 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
Qwen3.7-PlusAlibaba115Claude Opus 4.5 vs Qwen3.7-Plus
Qwen3.6 27BAlibaba115Claude Opus 4.5 vs Qwen3.6 27B
GPT-5 miniOpenAI115Claude Opus 4.5 vs GPT-5 mini
GLM-5.1Z.ai (Zhipu AI)116Claude Opus 4.5 vs GLM-5.1
InklingThinking Machines114Claude Opus 4.5 vs Inkling

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); Berkeley Function Calling Leaderboard, Gorilla project (Apache-2.0); Epoch AI, ‘Capabilities & benchmarking’ (CC BY 4.0); Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter..