---
title: "Claude 3.5 Haiku Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for Claude 3.5 Haiku."
source: "https://rankedagi.com/models/claude-3.5-haiku"
---

# Claude 3.5 Haiku

| Field | Value |
| --- | --- |
| Organization | Anthropic |
| License | Proprietary |
| Version | Latest |
| Released | 2024-10-22 |
| Context window | 200K |
| Knowledge cutoff | 2024-07-01 |
| Input cost per million tokens | $1 |
| Output cost per million tokens | $5 |
| Cached input cost per million tokens | $0.1 |
| Model ID | claude-3-5-haiku-20241022 |
| Last updated | 2026-05-04T01:34:22.840Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 35.3% | RankedAGI Coding Score |  |
| SWEBench Verified | coding | 40.6% | Agentic Coding | https://www.swebench.com/index.html |
| RankedAGI Agentic | Agents | 31.4% | RankedAGI Agentic Score |  |
| ChatArena (LMSYS) | coding | 1263 | ChatArena (LMSYS) Coding ELO Score with Style Control |  |
| Aider Polyglot | coding | 28.0% | Aider Polyglot Code Completion Benchmark |  |
| LiveBench Coding Score (old) | coding | 51.4% | LiveBench Coding Score old version |  |
| RankedAGI Reasoning | reasoning | 32.8% | RankedAGI Reasoning Score |  |
| GPQA Diamond | reasoning | 41.6% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| Text Arena | general | 1239 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| HumanEval | coding | 88.1% | HumanEval coding benchmark |  |
| NYT Connections Extended | reasoning | 10.3% | NYT Connections Extended Version | https://github.com/lechmazur/nyt-connections/ |
| MMLU Pro | knowledge | 65.0% | Graduate-level visual problem-solving |  |
| MMLU | knowledge | 81.0% | Image Reasoning |  |
| Hughes Hallucination Evaluation | safety | 4.9% | Computed using Vectara's Hallucination Evaluation Model, also known as HHEM. This evaluates how often an LLM introduces hallucinations when summarizing a document. | https://github.com/vectara/hallucination-leaderboard |
| AidanBench | general | 904 | AidanBench Score |  |
| LiveBench Average | general | 47.8% | LiveBench Average Score old version |  |
| LiveBench Data Analysis | general | 42.4% | LiveBench Data Analysis Score | https://livebench.ai/ |
| LiveBench Language | general | 35.4% | LiveBench Language Score | https://livebench.ai/ |
| Artificial Analysis Quality Index | general | 69 | Artificial Analysis Quality Index (third-party composite, deprecated) |  |
| RankedAGI Math | math | 44.2% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 39.0% | Overall RankedAGI score |  |
| SvelteBench old | coding | 73.3% | SvelteBench - Benchmark for Svelte (Old v1) | https://khromov.github.io/svelte-bench/v1/v1-benchmark-results-merged.html |