Neura Intelligence Index
Back to Leaderboard
Claude 3.5 Haiku
🇺🇸Anthropic· Claude 3.51y
Context:200K tokens
Input:$0.8/1M
Output:$4/1M
Neura Index
40.7
Rank #213—
highCategory Profile
Benchmark Scores (9)
reasoning
| Benchmark | Score | Source |
|---|---|---|
| ARC-Challenge | 91.8 | aggregated |
| GPQA Diamond | 41.6 | aggregated |
safety
| Benchmark | Score | Source |
|---|---|---|
| TruthfulQA | 63.5 | aggregated |
math
| Benchmark | Score |
|---|
Performance History
Similar Models
Frequently Asked Questions about Claude 3.5 Haiku
What is Claude 3.5 Haiku's Neura Intelligence Index score?▾
Claude 3.5 Haiku by Anthropic scores 40.7 out of 100 on the Neura Intelligence Index, ranking #213 among tracked AI models. This composite score is computed from 9 individual benchmarks across coding, math, reasoning, and language categories.
How much does Claude 3.5 Haiku cost to use?▾
Claude 3.5 Haiku costs $0.8/1M input tokens and $4/1M output tokens via API. At a typical 3:1 input-to-output ratio with 1M tokens/day usage, the estimated monthly cost is approximately $48.
Is Claude 3.5 Haiku open source?▾
No, Claude 3.5 Haiku is a proprietary model by Anthropic. It is only accessible via their API.
What is Claude 3.5 Haiku's context window?▾
Claude 3.5 Haiku supports a context window of 200K tokens, allowing it to process very long documents, codebases, and conversations in a single request.
What benchmark does Claude 3.5 Haiku perform best on?▾
Claude 3.5 Haiku achieves its highest score on Chatbot Arena Elo with an Elo rating of 1200. This benchmark evaluates lmsys chatbot arena — crowdsourced blind comparison elo rating from human preferences.