Kaggle Benchmarks

Indexed results from Kaggle Benchmarks. Each ranking retains its own metric and evaluation conditions.

MetaARTW — Evaluating metacognition through ART · MetaARTW static difficult-1

kaggleBenchmarks · Kaggle Benchmarks · MetaARTW — Evaluating metacognition through ART · MetaARTW static difficult-1 · score · Higher is better

  1. Google: Gemini 2.5 Progoogle0.22
  2. Google: Gemini 2.5 Flashgoogle0.12

MetaCog-160: Benchmarking AI Metacognitive · (Overall)

kaggleBenchmarks · Kaggle Benchmarks · MetaCog-160: Benchmarking AI Metacognitive · (Overall) · score · Higher is better

  1. Google: Gemini 2.5 Flashgoogle100

Measuring Progress Toward AGI: Human-AI Memory · color_memory_test

kaggleBenchmarks · Kaggle Benchmarks · Measuring Progress Toward AGI: Human-AI Memory · color_memory_test · score · Higher is better

  1. Google: Gemini 2.5 Flashgoogle0
  2. Google: Gemini 2.5 Progoogle0
  3. OpenAI: gpt-oss-120bopenai0
  4. OpenAI: gpt-oss-20bopenai0

GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-233

kaggleBenchmarks · Kaggle Benchmarks · GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-233 · percent · Higher is better

  1. OpenAI: GPT-5openai100%
  2. OpenAI: o4 Mini (batch)openai100%

MCBench · mcbench_metacognition

kaggleBenchmarks · Kaggle Benchmarks · MCBench · mcbench_metacognition · score · Higher is better

  1. Google: Gemini 2.5 Progoogle0.635

GCSG: In-Context Compositional Rule Learning · gcsg_t3_learning_curve

kaggleBenchmarks · Kaggle Benchmarks · GCSG: In-Context Compositional Rule Learning · gcsg_t3_learning_curve · score · Higher is better

  1. Google: Gemini 2.5 Flashgoogle0.313

GCSG: In-Context Compositional Rule Learning · gcsg_t4_productivity

kaggleBenchmarks · Kaggle Benchmarks · GCSG: In-Context Compositional Rule Learning · gcsg_t4_productivity · score · Higher is better

  1. Google: Gemini 2.5 Progoogle0.518
  2. Google: Gemini 2.5 Flashgoogle0.015

Does LLMs understand images? · analyze_solved_puzzle_and_identify_traffic_signs

kaggleBenchmarks · Kaggle Benchmarks · Does LLMs understand images? · analyze_solved_puzzle_and_identify_traffic_signs · score · Higher is better

  1. Google: Gemini 2.5 Flashgoogle0
  2. Google: Gemini 2.5 Progoogle0

Multimodal Functional Fixedness Evaluation Suite · mffes_alien_world_physics_bt

kaggleBenchmarks · Kaggle Benchmarks · Multimodal Functional Fixedness Evaluation Suite · mffes_alien_world_physics_bt · score · Higher is better

  1. Google: Gemini 2.5 Progoogle0.593
  2. Google: Gemini 2.5 Flashgoogle0.564

HedgeDecode · no_name_literal_restraint

kaggleBenchmarks · Kaggle Benchmarks · HedgeDecode · no_name_literal_restraint · score · Higher is better

  1. Google: Gemini 2.5 Flashgoogle0.417

Pore-Neutral-Drainage-Resilience-Audit · (Overall)

kaggleBenchmarks · Kaggle Benchmarks · Pore-Neutral-Drainage-Resilience-Audit · (Overall) · score · Higher is better

  1. Google: Gemini 2.5 Flashgoogle100
  2. Google: Gemini 2.5 Progoogle100
  3. OpenAI: gpt-oss-120bopenai0
  4. OpenAI: gpt-oss-20bopenai0

MABR · mabr_a_028_feature_flags

kaggleBenchmarks · Kaggle Benchmarks · MABR · mabr_a_028_feature_flags · score · Higher is better

  1. OpenAI: o3openai1
  2. OpenAI: gpt-oss-120bopenai0.825
  3. Google: Gemini 2.5 Flashgoogle0.5

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace