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 Haiku 4.5?

104 SI-IQ · 90% interval 99–108
Rank 67 of 80 ranked models · Plausible rank range 57–71

Claude Haiku 4.5 is a model from Anthropic, released on Oct 15, 2025. Its SI-IQ is 104 (90% interval 99–108), estimated from 7 benchmark results by 3 independent evaluators. Its strongest area is Agents and its weakest is Knowledge.

Facts

Developer: Anthropic
Released: Oct 15, 2025
Access: API access
Benchmarks used: 7 results from 3 evaluators

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

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	8.0%	89	Epoch AI	`claude-haiku-4-5-20251001_59K`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
MATH Level 5	Math	96.4%	108	Epoch AI	`claude-haiku-4-5-20251001_32K`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
OTIS Mock AIME 2024–2025	Math	66.7%	100	Epoch AI	`claude-haiku-4-5-20251001_32K`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
GPQA Diamond	Knowledge	71.2%	96	Epoch AI	`claude-haiku-4-5-20251001_32K`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
GPQA Diamond (OpenRouter run)	Knowledge	73.1%	101	OpenRouter	`anthropic/claude-4.5-haiku-20251001` Anthropic · first-party provider (1 of 4 rows)	Oct 18, 2026	OpenRouter benchmark datasets · data file
SimpleQA Verified	Knowledge	13.2%	84	Epoch AI	`claude-haiku-4-5-20251001`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
Berkeley Function Calling Leaderboard	Agents	68.7%	122	UC Berkeley (Gorilla)	`Claude-Haiku-4-5-20251001 (FC)`	Oct 18, 2026	Berkeley Function Calling Leaderboard · data file
τ²-bench Airline (OpenRouter run)	Agents	66.6%	114	OpenRouter	`anthropic/claude-4.5-haiku-20251001` Anthropic · first-party provider (1 of 4 rows)	Oct 18, 2026	OpenRouter benchmark datasets · data file

Human preference (Arena)

On the Arena leaderboard, where people vote between two anonymous answers, Claude Haiku 4.5 has a rating of 1,414 (1,412–1,417) from 149,199 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

Model	SI-IQ
o3-miniOpenAI	105	Claude Haiku 4.5 vs o3-mini
GPT-5 nanoOpenAI	105	Claude Haiku 4.5 vs GPT-5 nano
gpt-oss-120bOpenAI	106	Claude Haiku 4.5 vs gpt-oss-120b
MiniMax-M3MiniMax	108	Claude Haiku 4.5 vs MiniMax-M3
Claude 3.7 SonnetAnthropic	99	Claude Haiku 4.5 vs Claude 3.7 Sonnet

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..