Skip to content
ENTITY PROFILE / KNOWLEDGE GRAPH

TheoPhysEval benchmark

RSS

GPT-6-Astra solved 49 out of 50 problems on the TheoPhysEval benchmark Anthropic Opus 5.5 solved 92% of the problems on the TheoPhysEval benchmark Google Gemini 3.8 Flash solved 68% of the problems on the TheoPhysEval benchmark DeepSeek-V4.1-Flash solved 54% of the problems on the TheoPhysEval benchmark GLM 5.3 solved 42% of the problems on the TheoPhysEval benchmark The TheoPhysEval benchmark is available on the Hugging Face dataset· Entity summary generated by Graphiti

RELATIONS
6Relations
CURRENT
6Current
EVENTS
1Events
REPORTS
1Source reports
KNOWLEDGE ATLAS0 entities · 0 relations
No public neighbors yet
Explore all published links of a node; previously discovered relations remain visible.

Relation timeline

BY VALID-FROM DATE
  1. EvalEval CoalitionSOLVEDTheoPhysEval benchmark

    Anthropic Opus 5.5 solved 92% of the problems on the TheoPhysEval benchmark

    Current1 sourceEvalEval Coalition
  2. GLM-5.3SOLVEDTheoPhysEval benchmark

    GLM 5.3 solved 42% of the problems on the TheoPhysEval benchmark

    Current1 sourceGLM-5.3
  3. SWE-bench VerifiedSOLVEDTheoPhysEval benchmark

    Google Gemini 3.8 Flash solved 68% of the problems on the TheoPhysEval benchmark

    Current1 sourceSWE-bench Verified
  4. GPT-6 AstraSOLVEDTheoPhysEval benchmark

    GPT-6-Astra solved 49 out of 50 problems on the TheoPhysEval benchmark

    Current1 sourceGPT-6 Astra
  5. CV3 EvalSOLVEDTheoPhysEval benchmark

    DeepSeek-V4.1-Flash solved 54% of the problems on the TheoPhysEval benchmark

    Current1 sourceCV3 Eval
  6. TheoPhysEval benchmarkAVAILABLE ONIndirect Prompt Injection (IPI) benchmark

    The TheoPhysEval benchmark is available on the Hugging Face dataset

    Current1 sourceIndirect Prompt Injection (IPI) benchmark

Relations are facts Graphiti extracted from reports, not verbatim quotes. An end date means later reporting showed the relation no longer holds.

Events 1

Source reports 1