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 | Nvidia Nemotron 3.5 Lightning TEEnvidiaRemove | |
|---|---|---|
| Provider | nvidia | |
| Discovery tier | Efficient | Open weights |
| Added | May 20, 2025 | Sep 11, 2026 |
| Limits | ||
| Context window | 1.05MBest | 262.14K |
| Max output | 65.54K | 65.54K |
| Pricing, USD per 1M tokens | ||
| Input | $0.15 | $0.08Best |
| Output | $3.50 | $0.20Best |
| Cache read | $0.015Best | $0.04 |
| Performance | ||
| Request success (24h) | 99.3% | — |
| Benchmark indexes | ||
| Intelligence Index | 13.1Best | 12.9 |
| Coding Index | — | 26.8 |
| Math Index | 73.3 | — |
| Capabilities | ||
| Reasoning | Yes | Yes |
| Tools | No | Yes |
| Vision | Yes | No |
| Structured output | No | Yes |
| Reasoning effort | low, medium, high | none, 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
- Nvidia Nemotron 3.5 Lightning TEE
Intelligence Index
- Gemini 2.5 Flash 0520 Thinking13.1
- Nvidia Nemotron 3.5 Lightning TEE12.9
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: —
- Nvidia Nemotron 3.5 Lightning TEE: 26.8
Math Index
Composite of the math evaluations
- Gemini 2.5 Flash 0520 Thinking: 73.3
- Nvidia Nemotron 3.5 Lightning TEE: —
Agentic work
AutomationBench-AA
Workflow automation, penalized for guardrail violations
- Gemini 2.5 Flash 0520 Thinking: —
- Nvidia Nemotron 3.5 Lightning TEE: 0.8%
AutomationBench-AA tasks completed
Workflows finished end to end without a guardrail violation
- Gemini 2.5 Flash 0520 Thinking: —
- Nvidia Nemotron 3.5 Lightning TEE: 0.0%
AA-Briefcasev1.1
Agentic knowledge work, rated head to head
- Gemini 2.5 Flash 0520 Thinking: —
- Nvidia Nemotron 3.5 Lightning TEE: 506 Elo
GDPval-AAv2.1
Economically valuable occupational tasks, rated head to head
- Gemini 2.5 Flash 0520 Thinking: —
- Nvidia Nemotron 3.5 Lightning TEE: 638 Elo
Document reasoning
GDP.pdf
Professional reasoning over PDF documents, all-pass rate
- Gemini 2.5 Flash 0520 Thinking: —
- Nvidia Nemotron 3.5 Lightning TEE: 3.0%
AA-LCRv1.1
Reasoning across long documents
- Gemini 2.5 Flash 0520 Thinking: 65.3%Top
- Nvidia Nemotron 3.5 Lightning TEE: 60.3%
MLCR-AA
Long-context reasoning over medical records
- Gemini 2.5 Flash 0520 Thinking: —
- Nvidia Nemotron 3.5 Lightning TEE: 2.2%
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- Gemini 2.5 Flash 0520 Thinking: 12.1%Top
- Nvidia Nemotron 3.5 Lightning TEE: 10.6%
GPQA Diamond
Graduate-level science questions
- Gemini 2.5 Flash 0520 Thinking: 79.0%Top
- Nvidia Nemotron 3.5 Lightning TEE: 74.3%
MMLU-Pro
Multi-subject knowledge and reasoning
- Gemini 2.5 Flash 0520 Thinking: 83.2%
- Nvidia Nemotron 3.5 Lightning TEE: —
IFBench
Following precise output instructions
- Gemini 2.5 Flash 0520 Thinking: 50.3%
- Nvidia Nemotron 3.5 Lightning TEE: —
Coding
Terminal-Benchv4.0
Practical software engineering in a terminal
- Gemini 2.5 Flash 0520 Thinking: —
- Nvidia Nemotron 3.5 Lightning TEE: 0.5%
SciCode
Scientific computing in Python
- Gemini 2.5 Flash 0520 Thinking: —
- Nvidia Nemotron 3.5 Lightning TEE: 32.1%
LiveCodeBench
Recent competitive programming problems
- Gemini 2.5 Flash 0520 Thinking: 69.5%
- Nvidia Nemotron 3.5 Lightning TEE: —
Math
AIME 2025
Competition mathematics, 2025 problems
- Gemini 2.5 Flash 0520 Thinking: 73.3%
- Nvidia Nemotron 3.5 Lightning TEE: —
AIME
Competition mathematics
- Gemini 2.5 Flash 0520 Thinking: 82.3%
- Nvidia Nemotron 3.5 Lightning TEE: —
MATH-500
Competition math problems
- Gemini 2.5 Flash 0520 Thinking: 98.1%
- Nvidia Nemotron 3.5 Lightning TEE: —
Legacy evaluations
Terminal-Bench Hard
Earlier terminal task suite
- Gemini 2.5 Flash 0520 Thinking: 13.6%
- Nvidia Nemotron 3.5 Lightning TEE: —
τ²-Bench Telecom
Tool use in a customer-support simulation
- Gemini 2.5 Flash 0520 Thinking: 31.6%
- Nvidia Nemotron 3.5 Lightning TEE: —
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- Gemini 2.5 Flash 0520 Thinking: 65.3%Top
- Nvidia Nemotron 3.5 Lightning TEE: 60.3%
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.