ModelTape
All modelsNew releasesRankingsRuns on my GPUOpen the app →
ModelTape / Models / Claude 3.5 Haiku
Anthropic · API-only (closed weights)

Claude 3.5 Haiku

Claude 3.5 Haiku is an API-only (closed weights) language model from Anthropic, released October 22, 2024. On the Epoch Capabilities Index it scores 124.9, rank 174 of 256 rated models.

Check it against your own PC →

Lab
Anthropic
Released
October 22, 2024
Weights
API-only (closed weights)
Parameters
–
Context
–
Price / M tokens
–
Epoch ECI
124.9 #174

Strengths by category

ModelTape's 0–100 fit on Epoch AI benchmark results.

CategoryScoreBased on
Math12.1MATH level 5, OTIS Mock AIME 2024-2025, FrontierMath-2025-02-28-Private
Knowledge26.0GPQA diamond, MMLU

Benchmark results

Benchmark (Epoch AI)Score
MMLU65.7%
MATH level 546.4%
Aider Polyglot28.0%
Balrog19.3%
GPQA Diamond18.2%
OTIS Mock AIME4.2%
FrontierMath-2025-02-28-Private0.6%

Links

Epoch AI benchmarks

Models with a similar score

GPT-4o (Nov 2024) · GPT-4o (May 2024) · Llama 3.1-405B · Llama 4 Scout · Gemma 3 27B · Qwen2.5-72B · GPT-4o (Aug 2024) · Gemini 1.5 Flash (Sep 2024)

More from Anthropic

Claude Fable 5.2 · Claude Haiku 5.5 · Claude Sonnet 5.5 · Claude Opus 5.5 · Claude Fable 5.1 · Claude Opus 5 · Claude Sonnet 5 · Claude Fable 5

Data updated Thu, 12 Nov 2026 09:42 UTC. Benchmarks, Capabilities Index and model announcements: Epoch AI, “Capabilities & benchmarking” and “Data on AI models” (CC BY 4.0); category scores are ModelTape's own fit on Epoch's results. Releases and prices: models.dev (MIT). Sizes and quantizations: Hugging Face. “Runs on” figures are estimates from model size, quantization and memory bandwidth (±30–50%).
Live app · All models · New releases · Rankings · 6 GB · 8 GB · 12 GB · 16 GB · 24 GB · 32 GB · Legal notice (Impressum) · Privacy