Coverage (30d)
2vs13
This Week
1vs4
Evidence
1 articlesRelationships
0Timeline
DeepSeek V4-Pro2026-07-15
DeepSeek released V4-Pro and V4-Flash, open-weights models with up to 1.6 trillion parameters.
GPT-52026-05-11
Study reveals GPT-5 exhibits central tendency bias in clinical scoring, compressing predictions toward scale midpoint.
GPT-52026-03-06
Evaluation study published on arXiv assessing its clinical reasoning capabilities
GPT-52025-05-31
Reportedly became available according to user social media post
Ecosystem
DeepSeek V4-Pro
competes withKimi K2.61 src
competes withGLM-5.11 src
GPT-5
competes withMolmoAct21 src
competes withClaude Opus 4.71 src
usescentral tendency bias1 src
deploysChain-of-Thought Prompting1 src
deploysMixture of Experts (Sparse MoE for LLMs)1 src
Benchmarks
arena elo
DeepSeek V4-Pro—
GPT-51450
swe bench verified
DeepSeek V4-Pro—
GPT-580