modelgrep

Anthropic: Claude 3.5 Haiku vs OpenAI: GPT-4o (2024-08-06)

Anthropic: Claude 3.5 Haiku wins on more metrics (6 of 8), but the right pick depends on what you optimize for — see the breakdown below.

MetricAnthropic: Claude 3.5 HaikuOpenAI: GPT-4o (2024-08-06)
Intelligence Index18.718.6
Coding Index10.716.6
GPQA Diamond41%52%
Design Arena Elo
Speed (tokens/sec)3623
Latency785ms942ms
Input price /M$0.800$2.50
Output price /M$4.00$10.00
Context window200K128K
CapabilitiesToolsVisionToolsJSONVision