MDL
Gemini 2.0 Flash Thinking Experimental (Jan '25)
Verified against Artificial Analysis · Jul 13, 2026
Capability
71
percentile index
Price /M
$0 / $0
in / out
Context
—
Avg score
52.7
6 benchmarks
AA Intelligence
13.3
index
Weights
Closed
Released
Jan 21, 2025
About
Gemini 2.0 Flash Thinking Experimental (Jan '25) is a proprietary model in the Gemini family from Google. Benchmarked on 6 evals, averaging 52.7.
Benchmark scores · 6
avg 52.7 — higher is betterThe research behind this model
all papers mentioning it →Text-Preserving Lossy Text Compression: A Study of Strategic Deletion and LLM ReconstructionMay 27, 2026Blind Spots in the Guard: How Domain-Camouflaged Injection Attacks Evade Detection in Multi-Agent LLM SystemsMay 21, 2026Can We Trust AI-Inferred User States. A Psychometric Framework for Validating the Reliability of Users States Classification by LLMs in Operational EnvironmentsMay 15, 2026Knee Osteoarthritis Severity Grading Using Optimized Deep Learning and LLM-Driven Intelligent AI on Computationally Limited SystemsMay 7, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.
Performance & price
Price in / out$0 / $0 per 1M
Coding index24.1
Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →
History
full ledger →Capability over time
Append-only ledger — every observed change to this model's numbers.
API providers
Artificial Analysis$0/M