Inception says Mercury 3 beats GPT-6 Luna and Claude Haiku 5.5 at up to 8x the speed
SiliconANGLE Duncan Riley ● Covered by 2 sources
Inception AI released Mercury 3, claiming it outperforms GPT-6 Luna and Claude Haiku 5.5 on most tests and runs up to faster in inference. In its benchmarks, Mercury 3 reached 1,068 tokens per second on Nvidia GPUs versus about 130 for GPT-6 Luna and about 240 for Haiku 5.5. The release expands Inception’s approach of drafting responses in parallel and enables wider adoption in low-latency products, alongside new pricing at 20 cents per million input tokens and 70 cents per million output tokens.
Why it matters
Diffusion language model startup Inception AI Inc. today released Mercury 3, its new flagship model. In the company’s own benchmarks, Mercury 3 beat OpenAI Group PBC’s GPT-6 Luna and Anthropic PBC’s Claude Haiku 5.5 on eight of 12 tests at four to eight times their speed. The release takes on the main doubt about Inception’s […] The post Inception says Mercury 3 beats GPT-6 Luna and Claude Haiku 5.5 at up to 8x the speed appeared first on SiliconANGLE.
