Unverified50% confidenceFactExact time
The MERIT experiment adopted a pre-registered 3-model × 3-random-seed grid experiment using GPT-4.1 and Claude Haiku 4.5.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThis article tested the actual performance of three large models — GPT-4o Mini, Qwen Max, and local Llama 3.1 — in multi-agent scenarios.68% similarUnverifiedThe narrative instruction-following capability of quantized open-source small-parameter models such as Meta's Llama 3 series and Mistral AI's Mixtral series has approached the level of early GPT-3.5.67% similarUnverifiedThe experiment tested three AI models — Claude Opus 4.6, GPT Codex, and Gemini — across three dimensions: code generation, environment interaction, and tool invocation.66% similarUnverifiedOpenAI推出GPT-4o mini、Anthropic推出Claude 3.5 Haiku，均属于在同一基座上通过后训练迭代推出中间版本的策略66% similarVerifiedOpenAI的GPT-4o mini、Anthropic的Claude 3.5 Haiku等产品都在走轻量高效模型的类似路线65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/895508API
curl https://kongchang.com/api/v1/knowledge/claims/895508MCP
get_claim(id=895508)