Google · Efficient
Gemini 2.5 Flash 0520 Thinking
Deprecated. Mapped to Gemini 2.5 Flash because this model is deprecated
- Reasoning
- Vision
- Input
- Text, Images
- Output
- Text
- Reasoning effort
- low · medium · high
- Discovery tier
- Efficient
Pricing
USD per 1M tokens- Input
- $0.15
- Output
- $3.50
- Cache read
- $0.015
Reference prices as published by the model provider. API example
Specifications
- Context window
- 1M
- Max output
- 65.5K
Side by side
Gemini 2.5 Flash 0520 Thinking compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| Gemini 2.5 Flash 0520 ThinkingGoogleThis model | Gemini 3.5 Flash ThinkingGoogleRemove | |
|---|---|---|
| Provider | ||
| Discovery tier | Efficient | Efficient |
| Added | May 20, 2025 | May 19, 2026 |
| Limits | ||
| Context window | 1.05M | 1.05MBest |
| Max output | 65.54K | 65.54K |
| Average output | — | 1.7K tokens |
| Pricing, USD per 1M tokens | ||
| Input | $0.15Best | $1.50 |
| Output | $3.50Best | $9.00 |
| Cache read | $0.015Best | $0.15 |
| Cache write | — | $0.0833 |
| Performance | ||
| Throughput | — | 255.7 tok/s |
| Time to first token | — | 10.3 s |
| Request success (24h) | 99.3%Best | 89.7% |
| Benchmark indexes | ||
| Intelligence Index | 13.1 | 32.6Best |
| Coding Index | — | 70.1 |
| Math Index | 73.3 | — |
| Capabilities | ||
| Reasoning | Yes | Yes |
| Vision | Yes | Yes |
| Audio input | No | Yes |
| Video input | No | Yes |
| Reasoning effort | low, medium, high | minimal, low, medium, high |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- Gemini 2.5 Flash 0520 Thinking
- Gemini 3.5 Flash Thinking
Intelligence Index
- Gemini 2.5 Flash 0520 Thinking13.1
- Gemini 3.5 Flash Thinking32.6
Gemini 2.5 Flash 0520 Thinking: Better than 32% of 326 scored models
Indexes
Coding Index
Composite of the coding evaluations
- Gemini 2.5 Flash 0520 Thinking: —
- Gemini 3.5 Flash Thinking: 70.1
Math Index
Composite of the math evaluations
- Gemini 2.5 Flash 0520 Thinking: 73.3
- Gemini 3.5 Flash Thinking: —
Agentic work
AutomationBench-AA
Workflow automation, penalized for guardrail violations
- Gemini 2.5 Flash 0520 Thinking: —
- Gemini 3.5 Flash Thinking: 42.1%
AutomationBench-AA tasks completed
Workflows finished end to end without a guardrail violation
- Gemini 2.5 Flash 0520 Thinking: —
- Gemini 3.5 Flash Thinking: 13.5%
AA-Briefcasev1.1
Agentic knowledge work, rated head to head
- Gemini 2.5 Flash 0520 Thinking: —
- Gemini 3.5 Flash Thinking: 874 Elo
GDPval-AAv2.1
Economically valuable occupational tasks, rated head to head
- Gemini 2.5 Flash 0520 Thinking: —
- Gemini 3.5 Flash Thinking: 1,202 Elo
Document reasoning
GDP.pdf
Professional reasoning over PDF documents, all-pass rate
- Gemini 2.5 Flash 0520 Thinking: —
- Gemini 3.5 Flash Thinking: 19.8%
AA-LCRv1.1
Reasoning across long documents
- Gemini 2.5 Flash 0520 Thinking: 65.3%
- Gemini 3.5 Flash Thinking: 73.3%Top
MLCR-AA
Long-context reasoning over medical records
- Gemini 2.5 Flash 0520 Thinking: —
- Gemini 3.5 Flash Thinking: 10.0%
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- Gemini 2.5 Flash 0520 Thinking: 12.1%
- Gemini 3.5 Flash Thinking: 42.7%Top
GPQA Diamond
Graduate-level science questions
- Gemini 2.5 Flash 0520 Thinking: 79.0%
- Gemini 3.5 Flash Thinking: 92.2%Top
MMLU-Pro
Multi-subject knowledge and reasoning
- Gemini 2.5 Flash 0520 Thinking: 83.2%
- Gemini 3.5 Flash Thinking: —
IFBench
Following precise output instructions
- Gemini 2.5 Flash 0520 Thinking: 50.3%
- Gemini 3.5 Flash Thinking: 76.3%Top
Coding
Terminal-Benchv4.0
Practical software engineering in a terminal
- Gemini 2.5 Flash 0520 Thinking: —
- Gemini 3.5 Flash Thinking: 6.6%
SciCode
Scientific computing in Python
- Gemini 2.5 Flash 0520 Thinking: —
- Gemini 3.5 Flash Thinking: 53.9%
LiveCodeBench
Recent competitive programming problems
- Gemini 2.5 Flash 0520 Thinking: 69.5%
- Gemini 3.5 Flash Thinking: —
Math
AIME 2025
Competition mathematics, 2025 problems
- Gemini 2.5 Flash 0520 Thinking: 73.3%
- Gemini 3.5 Flash Thinking: —
AIME
Competition mathematics
- Gemini 2.5 Flash 0520 Thinking: 82.3%
- Gemini 3.5 Flash Thinking: —
MATH-500
Competition math problems
- Gemini 2.5 Flash 0520 Thinking: 98.1%
- Gemini 3.5 Flash Thinking: —
Legacy evaluations
Terminal-Bench Hard
Earlier terminal task suite
- Gemini 2.5 Flash 0520 Thinking: 13.6%
- Gemini 3.5 Flash Thinking: 40.9%Top
τ²-Bench Telecom
Tool use in a customer-support simulation
- Gemini 2.5 Flash 0520 Thinking: 31.6%
- Gemini 3.5 Flash Thinking: 95.3%Top
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- Gemini 2.5 Flash 0520 Thinking: 65.3%
- Gemini 3.5 Flash Thinking: 73.3%Top
Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis
Live routing data
Performance and reliability
Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.
- Request success (24h)
- 99.3%
- Reliable
- Healthy (98% or more)
- Degraded (90–98%)
- Down (under 90%)
- No requests
Developers
Use it through the API
Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.
curl https://www.noumen.xyz/api/v1/chat/completions \
-H "Authorization: Bearer $NOUMEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-2.5-flash-preview-05-20:thinking",
"reasoning_effort": "medium",
"messages": [{ "role": "user", "content": "Explain this stack trace." }]
}'import os
from openai import OpenAI
client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
model="gemini-2.5-flash-preview-05-20:thinking",
messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)Related models
Other Google models, starting with the same family.