Claude 3.5 HaikuvsGPT-5.6 Luna

Claude 3.5 Haiku
GPT-5.6 Luna
API pricing
Input price
$0.20
Output price
$1.20
Cached input price
$0.02
Benchmarks
BullshitBench v2
50%40%
Benchmarks
Gray Swan IPI · k = 1
8.3%
Gray Swan IPI · k = 10
38.6%
Gray Swan IPI · k = 15
43.9%
SWE-Bench Verified
40.6%
CursorBench v3.2
61.1%
Frontier-Bench v0.1
14.3%
Terminal-Bench 2.1
82.5%
GPQA Diamond
41.6%
Arena Elo (Code)
1517
Overview
CompanyAnthropicOpenAI
Release dateOct 22 2024Jun 26 2026
AccessProprietaryProprietary

Frequently asked questions

Claude 3.5 Haiku leads GPT-5.6 Luna on 1 of the 1 benchmark they both report (BullshitBench v2). Only GPT-5.6 Luna has a verified first-party API price: $0.20 per million input tokens and $1.20 per million output tokens. No pay-as-you-go API rate is tracked for Claude 3.5 Haiku. Claude 3.5 Haiku shipped 612 days before GPT-5.6 Luna, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On BullshitBench v2, Claude 3.5 Haiku leads at 50% vs GPT-5.6 Luna at 40%.

Claude 3.5 Haiku was released by Anthropic on Oct 22 2024.

GPT-5.6 Luna was released by OpenAI on Jun 26 2026.

Only GPT-5.6 Luna has a verified first-party API price: $0.20 per million input tokens and $1.20 per million output tokens. No pay-as-you-go API rate is tracked for Claude 3.5 Haiku. Rates are pay-as-you-go API prices verified on August 18, 2026.

Other comparisons