Skip to content
ENTITY PROFILE / KNOWLEDGE GRAPH

Taste-Bench

RSS

Taste-Bench was published by The Decoder GPT-5.6 Sol was the best performing model on Taste-Bench GPT-5.5 was the second best performing model on Taste-Bench Claude was tested on Taste-Bench Grok was tested on Taste-Bench DeepSeek was tested on Taste-Bench GLM was tested on Taste-Bench MiniMax was tested on Taste-Bench Mistral was tested on Taste-Bench SWE-bench Pro provided data for Taste-Bench METR's public transcript release MALT provided data for Taste-Bench Qwen3.6-27B was used as a base model for Taste-Bench training Indra runs 15× faster than Tesseract OCR on CPU Datalab released Indra, a 1M-parameter OCR model· Entity summary generated by Graphiti

RELATIONS
14Relations
CURRENT
13Current
EVENTS
2Events
REPORTS
2Source 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. GPT-5.6 SolBEST MODEL ONTaste-Bench

    GPT-5.6 Sol was the best performing model on Taste-Bench

    Current1 sourceGPT-5.6 Sol
  2. METR's public transcript release MALTPROVIDED DATA FORTaste-Bench

    METR's public transcript release MALT provided data for Taste-Bench

    Current1 sourceMETR's public transcript release MALT
  3. CollabBenchTESTED ONTaste-Bench

    MiniMax was tested on Taste-Bench

    Current1 sourceCollabBench
  4. ClaudeTESTED ONTaste-Bench

    Claude was tested on Taste-Bench

    Current1 sourceClaude
  5. SWE-benchPROVIDED DATA FORTaste-Bench

    SWE-bench Pro provided data for Taste-Bench

    Current1 sourceSWE-bench
  6. DeepseekTESTED ONTaste-Bench

    DeepSeek was tested on Taste-Bench

    Current1 sourceDeepseek
  7. Grok 4.7TESTED ONTaste-Bench

    Grok was tested on Taste-Bench

    Current1 sourceGrok 4.7
  8. Ray‑BanTESTED ONTaste-Bench

    GLM was tested on Taste-Bench

    Current1 sourceRay‑Ban
  9. Taste-BenchPUBLISHED BYTHE DECODER

    Taste-Bench was published by The Decoder

    Current1 sourceTHE DECODER
  10. MistralTESTED ONTaste-Bench

    Mistral was tested on Taste-Bench

    Current1 sourceMistral
  11. TeraWulfUSED AS BASE MODEL FORTaste-Bench

    Qwen3.6-27B was used as a base model for Taste-Bench training

    Current1 sourceTeraWulf
  12. GPT-5.5SECOND BEST MODEL ONTaste-Bench

    GPT-5.5 was the second best performing model on Taste-Bench

    Ended 2026-10-231 sourceGPT-5.5
  13. Taste-BenchOUTPERFORMSTasteVal

    Indra runs 15× faster than Tesseract OCR on CPU

    Current1 sourceTasteVal
  14. High Taste Testers Episode OneRELEASEDTaste-Bench

    Datalab released Indra, a 1M-parameter OCR model

    Current1 sourceHigh Taste Testers Episode One

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

Events 2

Source reports 2